taufeeque/mbpp-hardcode
Viewer
• Updated
• 974 • 1.39k
The Obfuscation Altas
Obfuscated Policy, Obfuscated Activations, Blatant Deception, and Honest models trained in the Obfuscation Atlas paper
Note Dataset used for probe evaluation and RL training.
-
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.001-det10-seed1-mbpp_probe
Updated • 21 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.0001-det10-seed1-mbpp_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.01-det10-seed1-mbpp_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.0001-det3-seed1-mbpp_probe
Updated • 9 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.1-det3-seed1-mbpp_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.1-det10-seed1-mbpp_probe
Updated • 9 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl1-det3-seed1-mbpp_probe
Updated • 11 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl1-det10-seed1-mbpp_probe
Updated • 10 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.001-det3-seed1-mbpp_probe
Updated • 14 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl1-det10-seed1-mbpp_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.1-det10-seed1-mbpp_probe
Updated • 11 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.0001-det3-seed1-mbpp_probe
Updated • 11 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.01-det3-seed1-mbpp_probe
Updated • 14 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.01-det10-seed1-mbpp_probe
Updated • 16 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.001-det10-seed1-mbpp_probe
Updated • 8 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.0001-det10-seed1-mbpp_probe
Updated • 16 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.001-det3-seed1-mbpp_probe
Updated • 8 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.01-det3-seed1-mbpp_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.1-det3-seed1-diverse_deception_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.1-det3-seed1-mbpp_probe
Updated • 8 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl1-det3-seed1-mbpp_probe
Updated • 10 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.1-det10-seed1-diverse_deception_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.1-det1-seed1-diverse_deception_probe
Updated • 14 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.01-det3-seed1-mbpp_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.1-det3-seed1-mbpp_probe
Updated • 11 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.001-det3-seed1-mbpp_probe
Updated • 11 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.0001-det3-seed1-mbpp_probe
Updated • 18 • 1 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.1-det1-seed1-diverse_deception_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.1-det10-seed1-diverse_deception_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.1-det1-seed1-diverse_deception_probe
Updated • 14 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl1-det3-seed1-mbpp_probe
Updated • 10 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.01-det10-seed1-mbpp_probe
Updated • 8 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.01-det1-seed1-deception_probe
Updated • 14 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.1-det1-seed1-mbpp_probe
Updated • 15 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.01-det10-seed1-deception_probe
Updated • 17 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.01-det3-seed1-deception_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.1-det3-seed1-deception_probe
Updated • 14 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.1-det1-seed1-deception_probe
Updated • 14 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.01-det1-seed1-deception_probe
Updated • 15 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.1-det3-seed1-diverse_deception_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.1-det1-seed1-mbpp_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.1-det10-seed1-deception_probe
Updated • 14 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.001-det10-seed1-mbpp_probe
Updated • 11 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.1-det10-seed1-diverse_deception_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.0001-det10-seed1-mbpp_probe
Updated • 14 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.1-det10-seed1-mbpp_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl1-det10-seed1-mbpp_probe
Updated • 11 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.1-det1-seed1-deception_probe
Updated • 14 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.01-det3-seed1-deception_probe
Updated • 9 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.1-det10-seed1-deception_probe
Updated • 11 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.01-det10-seed1-deception_probe
Updated • 16 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.1-det3-seed1-deception_probe
Updated • 17 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.0001-det3-seed1-diverse_deception_probe
Updated • 16 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-70B-Instruct-kl0.1-det3-seed1-diverse_deception_probe
Updated • 15 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-70B-Instruct-kl0.1-det1-seed1-diverse_deception_probe
Updated • 14 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.0001-det3-seed1-deception_probe
Updated • 14 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.0001-det10-seed1-deception_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.001-det10-seed1-deception_probe
Updated • 14 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.0001-det3-seed1-diverse_deception_probe
Updated • 11 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.1-det1-seed1-deception_probe
Updated • 14 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.1-det10-seed1-deception_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl1-det1-seed1-deception_probe
Updated • 9 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.001-det1-seed1-deception_probe
Updated • 11 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl1-det10-seed1-deception_probe
Updated • 16 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.0001-det10-seed1-deception_probe
Updated • 17 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.1-det3-seed1-deception_probe
Updated • 10 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.0001-det10-seed1-diverse_deception_probe
Updated • 14 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.0001-det100-seed1-mbpp_probe
Updated • 14 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.0001-det10-seed1-deception_probe
Updated • 11 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-70B-Instruct-kl0.1-det10-seed1-diverse_deception_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.001-det3-seed1-deception_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl1-det3-seed1-deception_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.0001-det3-seed1-deception_probe
Updated • 11 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.001-det1-seed1-mbpp_probe
Updated • 10 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.01-det1-seed1-mbpp_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl1-det1-seed1-mbpp_probe
Updated • 15 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.1-det100-seed1-mbpp_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl1-det3-seed1-diverse_deception_probe
Updated • 11 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl1-det10-seed1-diverse_deception_probe
Updated • 11 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.0001-det100-seed1-mbpp_probe
Updated • 16 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.0001-det1-seed1-diverse_deception_probe
Updated • 14 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl1-det1-seed1-diverse_deception_probe
Updated • 10 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.001-det1-seed1-mbpp_probe
Updated • 16 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl1-det1-seed1-mbpp_probe
Updated • 11 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl1-det1-seed1-diverse_deception_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl1-det3-seed1-diverse_deception_probe
Updated • 9 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.001-det1-seed1-diverse_deception_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.0001-det1-seed1-deception_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.01-det1-seed1-diverse_deception_probe
Updated • 276 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.0001-det1-seed1-diverse_deception_probe
Updated • 9 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.001-det3-seed1-diverse_deception_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.0001-det1-seed1-deception_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.01-det3-seed1-diverse_deception_probe
Updated • 18 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.01-det1-seed1-mbpp_probe
Updated • 11 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl1-det10-seed1-diverse_deception_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.001-det1-seed1-diverse_deception_probe
Updated • 14 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.001-det10-seed1-diverse_deception_probe
Updated • 8 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.0001-det10-seed1-diverse_deception_probe
Updated • 248 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.01-det3-seed1-diverse_deception_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.001-det3-seed1-diverse_deception_probe
Updated • 16 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.01-det1-seed1-diverse_deception_probe
Updated • 248 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.1-det100-seed1-diverse_deception_probe
Updated • 15 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.1-det3-seed1-diverse_deception_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.1-det100-seed1-diverse_deception_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl1-det1-seed1-mbpp_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.001-det1-seed1-mbpp_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.0001-det1-seed1-deception_probe
Updated • 11 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.1-det1-seed1-mbpp_probe
Updated • 17 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.01-det1-seed1-mbpp_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.0001-det1-seed1-mbpp_probe
Updated • 11 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.01-det10-seed1-diverse_deception_probe
Updated • 9 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.001-det3-seed1-deception_probe
Updated • 9 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl1-det3-seed1-deception_probe
Updated • 16 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.001-det1-seed1-deception_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.001-det10-seed1-deception_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl1-det1-seed1-deception_probe
Updated • 9 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl1-det10-seed1-deception_probe
Updated • 9 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.01-det10-seed1-diverse_deception_probe
Updated • 16 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.0001-det10-seed1-diverse_deception_probe
Updated • 239 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.001-det10-seed1-diverse_deception_probe
Updated • 14 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-70B-Instruct-kl0.0001-det3-seed1-diverse_deception_probe
Updated • 15 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-70B-Instruct-kl0.0001-det10-seed1-diverse_deception_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.01-det3-seed1-diverse_deception_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.001-det3-seed1-diverse_deception_probe
Updated • 11 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl1-det3-seed1-diverse_deception_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl1-det10-seed1-diverse_deception_probe
Updated • 10 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.001-det10-seed1-diverse_deception_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.01-det10-seed1-diverse_deception_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.01-det1-seed1-diverse_deception_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.001-det1-seed1-diverse_deception_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl1-det1-seed1-diverse_deception_probe
Updated • 8 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.001-det1-seed1-deception_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl1-det3-seed1-deception_probe
Updated • 15 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.01-det1-seed1-deception_probe
Updated • 14 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl1-det1-seed1-deception_probe
Updated • 15 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.0001-det100-seed1-mbpp_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.1-det100-seed1-diverse_deception_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.0001-det3-seed1-diverse_deception_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.0001-det100-seed1-diverse_deception_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.0001-det100-seed1-diverse_deception_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.0001-det3-seed1-deception_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.0001-det100-seed1-diverse_deception_probe
Updated • 14 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.0001-det1-seed1-diverse_deception_probe
Updated • 14 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.001-det10-seed2-mbpp_probe
Updated • 14 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.1-det10-seed2-mbpp_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.01-det3-seed2-mbpp_probe
Updated • 11 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl1-det10-seed2-mbpp_probe
Updated • 15 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.001-det3-seed2-mbpp_probe
Updated • 17 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.0001-det10-seed2-mbpp_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.0001-det3-seed2-mbpp_probe
Updated • 11 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.01-det3-seed2-mbpp_probe
Updated • 10 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.01-det10-seed2-mbpp_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.001-det10-seed2-mbpp_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.0001-det10-seed2-mbpp_probe
Updated • 11 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.0001-det3-seed2-mbpp_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.1-det10-seed2-mbpp_probe
Updated • 11 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.001-det3-seed2-mbpp_probe
Updated • 11 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.1-det3-seed2-mbpp_probe
Updated • 15 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.01-det10-seed2-mbpp_probe
Updated • 10 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl1-det10-seed2-mbpp_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl1-det3-seed2-mbpp_probe
Updated • 11 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.1-det1-seed2-diverse_deception_probe
Updated • 8 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl1-det3-seed2-mbpp_probe
Updated • 14 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.1-det3-seed2-mbpp_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.1-det10-seed2-diverse_deception_probe
Updated • 14 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.1-det3-seed2-diverse_deception_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.01-det3-seed2-mbpp_probe
Updated • 11 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.001-det3-seed2-mbpp_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.0001-det3-seed2-mbpp_probe
Updated • 8 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.0001-det10-seed2-mbpp_probe
Updated • 11 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.1-det3-seed2-mbpp_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.1-det10-seed2-mbpp_probe
Updated • 9 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl1-det3-seed2-mbpp_probe
Updated • 14 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.01-det10-seed2-mbpp_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.1-det1-seed2-diverse_deception_probe
Updated • 10 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.1-det1-seed2-mbpp_probe
Updated • 10 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.01-det1-seed2-deception_probe
Updated • 11 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.1-det1-seed2-deception_probe
Updated • 15 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.01-det10-seed2-deception_probe
Updated • 14 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.1-det3-seed2-deception_probe
Updated • 14 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.1-det3-seed2-diverse_deception_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.1-det1-seed2-mbpp_probe
Updated • 15 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.1-det10-seed2-diverse_deception_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.01-det3-seed2-deception_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.1-det1-seed2-diverse_deception_probe
Updated • 10 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.1-det10-seed2-deception_probe
Updated • 14 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.1-det10-seed2-diverse_deception_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl1-det10-seed2-mbpp_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.1-det3-seed2-diverse_deception_probe
Updated • 11 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.1-det1-seed2-deception_probe
Updated • 16 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.001-det10-seed2-mbpp_probe
Updated • 11 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.01-det3-seed2-deception_probe
Updated • 14 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.1-det10-seed2-deception_probe
Updated • 14 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.01-det1-seed2-deception_probe
Updated • 11 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.01-det10-seed2-deception_probe
Updated • 18 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.1-det3-seed2-deception_probe
Updated • 11 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.0001-det3-seed2-diverse_deception_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-70B-Instruct-kl0.1-det1-seed2-diverse_deception_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-70B-Instruct-kl0.1-det10-seed2-diverse_deception_probe
Updated • 11 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.0001-det10-seed2-deception_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.1-det3-seed2-deception_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.1-det10-seed2-deception_probe
Updated • 16 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.0001-det3-seed2-deception_probe
Updated • 15 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.0001-det3-seed2-diverse_deception_probe
Updated • 17 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.1-det1-seed2-deception_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.0001-det10-seed2-deception_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-70B-Instruct-kl0.1-det3-seed2-diverse_deception_probe
Updated • 11 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.0001-det3-seed2-diverse_deception_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl1-det3-seed2-deception_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.0001-det3-seed2-deception_probe
Updated • 11 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.001-det10-seed2-deception_probe
Updated • 9 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.0001-det100-seed2-mbpp_probe
Updated • 14 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.1-det100-seed2-mbpp_probe
Updated • 14 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.001-det3-seed2-deception_probe
Updated • 11 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.1-det100-seed2-mbpp_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl1-det1-seed2-deception_probe
Updated • 17 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.0001-det10-seed2-diverse_deception_probe
Updated • 11 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.0001-det100-seed2-mbpp_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl1-det10-seed2-deception_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.0001-det10-seed2-deception_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.001-det1-seed2-deception_probe
Updated • 14 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.0001-det100-seed2-mbpp_probe
Updated • 11 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.01-det1-seed2-mbpp_probe
Updated • 15 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.001-det1-seed2-mbpp_probe
Updated • 14 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.0001-det3-seed2-deception_probe
Updated • 14 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl1-det1-seed2-mbpp_probe
Updated • 10 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl1-det1-seed2-diverse_deception_probe
Updated • 14 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.001-det3-seed2-diverse_deception_probe
Updated • 15 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.01-det3-seed2-diverse_deception_probe
Updated • 14 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.001-det1-seed2-diverse_deception_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.001-det1-seed2-mbpp_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl1-det10-seed2-diverse_deception_probe
Updated • 10 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.001-det3-seed2-diverse_deception_probe
Updated • 15 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl1-det1-seed2-mbpp_probe
Updated • 14 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.0001-det1-seed2-diverse_deception_probe
Updated • 14 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-70B-Instruct-kl0.0001-det10-seed2-diverse_deception_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl1-det10-seed2-diverse_deception_probe
Updated • 11 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.01-det1-seed2-diverse_deception_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.0001-det1-seed2-deception_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl1-det3-seed2-diverse_deception_probe
Updated • 15 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.0001-det1-seed2-diverse_deception_probe
Updated • 15 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl1-det1-seed2-diverse_deception_probe
Updated • 9 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.01-det1-seed2-mbpp_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.0001-det1-seed2-deception_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.001-det1-seed2-diverse_deception_probe
Updated • 10 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl1-det3-seed2-diverse_deception_probe
Updated • 11 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.1-det100-seed2-diverse_deception_probe
Updated • 17 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.0001-det100-seed2-diverse_deception_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.0001-det1-seed2-mbpp_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.01-det1-seed2-mbpp_probe
Updated • 15 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.1-det100-seed2-diverse_deception_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl1-det1-seed2-mbpp_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.001-det1-seed2-mbpp_probe
Updated • 14 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.1-det1-seed2-mbpp_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.01-det3-seed2-diverse_deception_probe
Updated • 17 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.0001-det1-seed2-diverse_deception_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.0001-det100-seed2-diverse_deception_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.0001-det1-seed2-deception_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.001-det1-seed2-deception_probe
Updated • 19 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.01-det1-seed2-diverse_deception_probe
Updated • 14 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.001-det10-seed2-deception_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.001-det3-seed2-deception_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl1-det1-seed2-deception_probe
Updated • 14 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl1-det10-seed2-deception_probe
Updated • 17 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl1-det3-seed2-deception_probe
Updated • 18 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.1-det100-seed2-diverse_deception_probe
Updated • 15 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.0001-det10-seed2-diverse_deception_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.0001-det10-seed2-diverse_deception_probe
Updated • 14 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.001-det10-seed2-diverse_deception_probe
Updated • 11 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.01-det10-seed2-diverse_deception_probe
Updated • 10 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.001-det10-seed2-diverse_deception_probe
Updated • 15 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.01-det10-seed2-diverse_deception_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-70B-Instruct-kl0.0001-det1-seed2-diverse_deception_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl1-det3-seed2-diverse_deception_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.01-det10-seed2-diverse_deception_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.01-det3-seed2-diverse_deception_probe
Updated • 14 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl1-det10-seed2-diverse_deception_probe
Updated • 14 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.001-det10-seed2-diverse_deception_probe
Updated • 11 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.01-det1-seed2-diverse_deception_probe
Updated • 14 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.001-det1-seed2-diverse_deception_probe
Updated • 14 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl1-det1-seed2-diverse_deception_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.001-det3-seed2-diverse_deception_probe
Updated • 16 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.01-det1-seed2-deception_probe
Updated • 18 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.001-det1-seed2-deception_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-70B-Instruct-kl0.0001-det3-seed2-diverse_deception_probe
Updated • 15 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl1-det10-seed3-mbpp_probe
Updated • 14 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.001-det10-seed3-mbpp_probe
Updated • 14 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.0001-det10-seed3-mbpp_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl1-det3-seed3-mbpp_probe
Updated • 14 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl1-det3-seed3-mbpp_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.001-det10-seed3-mbpp_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.0001-det10-seed3-mbpp_probe
Updated • 10 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.1-det10-seed3-mbpp_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.01-det3-seed3-mbpp_probe
Updated • 16 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.0001-det3-seed3-mbpp_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.001-det3-seed3-mbpp_probe
Updated • 15 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.1-det10-seed3-mbpp_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.01-det10-seed3-mbpp_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.01-det10-seed3-mbpp_probe
Updated • 11 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl1-det10-seed3-mbpp_probe
Updated • 10 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.01-det3-seed3-mbpp_probe
Updated • 10 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.1-det3-seed3-mbpp_probe
Updated • 10 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.1-det3-seed3-diverse_deception_probe
Updated • 11 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.1-det3-seed3-mbpp_probe
Updated • 17 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.1-det3-seed3-diverse_deception_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.1-det10-seed3-diverse_deception_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.001-det3-seed3-mbpp_probe
Updated • 11 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.1-det1-seed3-diverse_deception_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.1-det10-seed3-diverse_deception_probe
Updated • 15 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.01-det3-seed3-mbpp_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl1-det10-seed3-mbpp_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.0001-det10-seed3-mbpp_probe
Updated • 16 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.0001-det3-seed3-mbpp_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.1-det1-seed3-diverse_deception_probe
Updated • 14 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.001-det10-seed3-mbpp_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.0001-det3-seed3-mbpp_probe
Updated • 10 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl1-det3-seed3-mbpp_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.001-det3-seed3-mbpp_probe
Updated • 15 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.1-det3-seed3-mbpp_probe
Updated • 16 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.01-det10-seed3-mbpp_probe
Updated • 11 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.01-det1-seed3-deception_probe
Updated • 10 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.1-det10-seed3-mbpp_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.1-det3-seed3-deception_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.1-det1-seed3-mbpp_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.01-det3-seed3-deception_probe
Updated • 9 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.1-det1-seed3-deception_probe
Updated • 15 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.1-det3-seed3-diverse_deception_probe
Updated • 10 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.1-det1-seed3-diverse_deception_probe
Updated • 11 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.1-det1-seed3-mbpp_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.1-det10-seed3-deception_probe
Updated • 10 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.1-det10-seed3-diverse_deception_probe
Updated • 16 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.01-det10-seed3-deception_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.1-det1-seed3-deception_probe
Updated • 18 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.01-det1-seed3-deception_probe
Updated • 11 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.1-det10-seed3-deception_probe
Updated • 11 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.01-det10-seed3-deception_probe
Updated • 10 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.1-det3-seed3-deception_probe
Updated • 9 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.01-det3-seed3-deception_probe
Updated • 9 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.0001-det3-seed3-diverse_deception_probe
Updated • 9 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.0001-det10-seed3-deception_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.0001-det3-seed3-deception_probe
Updated • 14 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.1-det3-seed3-deception_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.1-det1-seed3-deception_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.1-det10-seed3-deception_probe
Updated • 11 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-70B-Instruct-kl0.1-det1-seed3-diverse_deception_probe
Updated • 10 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.0001-det3-seed3-diverse_deception_probe
Updated • 10 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.0001-det10-seed3-deception_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.001-det10-seed3-deception_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.0001-det100-seed3-mbpp_probe
Updated • 11 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.1-det100-seed3-mbpp_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl1-det3-seed3-deception_probe
Updated • 11 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.0001-det3-seed3-deception_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-70B-Instruct-kl0.1-det3-seed3-diverse_deception_probe
Updated • 11 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-70B-Instruct-kl0.1-det10-seed3-diverse_deception_probe
Updated • 15 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.0001-det10-seed3-diverse_deception_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl1-det10-seed3-deception_probe
Updated • 15 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl1-det1-seed3-deception_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.001-det3-seed3-deception_probe
Updated • 17 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.0001-det10-seed3-deception_probe
Updated • 19 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.0001-det100-seed3-mbpp_probe
Updated • 19 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.001-det1-seed3-deception_probe
Updated • 11 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.0001-det3-seed3-deception_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.0001-det100-seed3-mbpp_probe
Updated • 14 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.001-det1-seed3-mbpp_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.01-det1-seed3-mbpp_probe
Updated • 16 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl1-det1-seed3-diverse_deception_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl1-det3-seed3-diverse_deception_probe
Updated • 14 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-70B-Instruct-kl0.0001-det1-seed3-diverse_deception_probe
Updated • 15 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl1-det10-seed3-diverse_deception_probe
Updated • 10 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.001-det3-seed3-diverse_deception_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl1-det1-seed3-mbpp_probe
Updated • 16 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl1-det1-seed3-diverse_deception_probe
Updated • 10 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.001-det1-seed3-diverse_deception_probe
Updated • 15 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.0001-det1-seed3-deception_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl1-det10-seed3-diverse_deception_probe
Updated • 10 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.0001-det1-seed3-deception_probe
Updated • 8 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.0001-det1-seed3-diverse_deception_probe
Updated • 17 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl1-det3-seed3-diverse_deception_probe
Updated • 9 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.001-det1-seed3-diverse_deception_probe
Updated • 14 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.01-det1-seed3-mbpp_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.001-det3-seed3-diverse_deception_probe
Updated • 10 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.01-det1-seed3-diverse_deception_probe
Updated • 18 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl1-det1-seed3-mbpp_probe
Updated • 8 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.001-det1-seed3-mbpp_probe
Updated • 11 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.0001-det1-seed3-diverse_deception_probe
Updated • 8 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.1-det100-seed3-diverse_deception_probe
Updated • 11 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.01-det3-seed3-diverse_deception_probe
Updated • 15 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.0001-det100-seed3-diverse_deception_probe
Updated • 17 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.001-det1-seed3-mbpp_probe
Updated • 11 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.0001-det1-seed3-mbpp_probe
Updated • 11 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl1-det1-seed3-mbpp_probe
Updated • 17 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.01-det1-seed3-mbpp_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.0001-det100-seed3-diverse_deception_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.0001-det1-seed3-diverse_deception_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.01-det3-seed3-diverse_deception_probe
Updated • 10 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.0001-det3-seed3-diverse_deception_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.1-det100-seed3-diverse_deception_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.001-det1-seed3-deception_probe
Updated • 8 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.0001-det1-seed3-deception_probe
Updated • 11 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.001-det3-seed3-deception_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.001-det10-seed3-deception_probe
Updated • 17 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.1-det1-seed3-mbpp_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.01-det10-seed3-diverse_deception_probe
Updated • 14 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.1-det100-seed3-diverse_deception_probe
Updated • 15 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl1-det3-seed3-deception_probe
Updated • 15 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl1-det10-seed3-deception_probe
Updated • 16 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.0001-det10-seed3-diverse_deception_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl1-det1-seed3-deception_probe
Updated • 14 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.001-det10-seed3-diverse_deception_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.01-det1-seed3-diverse_deception_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.0001-det10-seed3-diverse_deception_probe
Updated • 14 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.01-det10-seed3-diverse_deception_probe
Updated • 15 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.001-det10-seed3-diverse_deception_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.01-det3-seed3-diverse_deception_probe
Updated • 11 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.0001-det100-seed3-diverse_deception_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl1-det3-seed3-diverse_deception_probe
Updated • 15 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.01-det1-seed3-diverse_deception_probe
Updated • 11 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.01-det10-seed3-diverse_deception_probe
Updated • 11 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl1-det1-seed3-diverse_deception_probe
Updated • 11 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.001-det10-seed3-diverse_deception_probe
Updated • 14 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.001-det3-seed3-diverse_deception_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.001-det1-seed3-diverse_deception_probe
Updated • 13 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.001-det3-seed3-deception_probe
Updated • 10 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.001-det1-seed3-deception_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl1-det10-seed3-diverse_deception_probe
Updated • 15 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl1-det1-seed3-deception_probe
Updated • 15 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.01-det1-seed3-deception_probe
Updated • 14 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.0001-det1-seed3-mbpp_probe
Updated • 10 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl1-det3-seed3-deception_probe
Updated • 12 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.0001-det1-seed3-mbpp_probe
Updated • 17 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-70B-Instruct-kl0.0001-det3-seed3-diverse_deception_probe
Updated • 6 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.01-det10-seed3-deception_probe
Updated • 16 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl1-det10-seed3-deception_probe
Updated • 11 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.01-det3-seed3-deception_probe
Updated • 15 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.001-det10-seed3-deception_probe
Updated • 11 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.01-det0-seed1
Updated • 12 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl1-det0-seed1
Updated • 262 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.1-det0-seed1
Updated • 11 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0-det0-seed1
Updated • 12 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.001-det0-seed1
Updated • 9 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0-det0-seed1
Updated • 7 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.1-det0-seed1
Updated • 12 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.001-det0-seed1
Updated • 9 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.0001-det0-seed1
Updated • 10 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl1-det0-seed1
Updated • 380 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.01-det0-seed1
Updated • 11 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.0001-det0-seed1
Updated • 15 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.0001-det0-seed1
Updated • 14 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.0001-det0-seed2
Updated • 13 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0-det0-seed1
Updated • 14 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.1-det0-seed1
Updated • 14 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.01-det0-seed1
Updated • 10 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.001-det0-seed1
Updated • 13 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl1-det0-seed1
Updated • 13 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.0001-det0-seed3
Updated • 11 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-70B-Instruct-kl0.0001-det0-seed1
Updated • 13 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.0001-det0-seed2
Updated • 14 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-70B-Instruct-kl0.001-det0-seed1
Updated • 11 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.0001-det0-seed3
Updated • 12 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.0001-det0-seed3
Updated • 15 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.001-det0-seed2
Updated • 12 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.0001-det0-seed2
Updated • 12 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-70B-Instruct-kl0.1-det0-seed1
Updated • 12 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-70B-Instruct-kl1-det0-seed1
Updated • 10 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.01-det0-seed3
Updated • 9 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.001-det0-seed3
Updated • 12 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.1-det0-seed3
Updated • 10 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.01-det0-seed2
Updated • 12 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl1-det0-seed2
Updated • 12 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.001-det0-seed2
Updated • 14 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.01-det0-seed3
Updated • 14 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.1-det0-seed3
Updated • 9 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.01-det0-seed2
Updated • 12 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.1-det0-seed2
Updated • 14 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl1-det0-seed3
Updated • 9 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-70B-Instruct-kl0.0001-det0-seed3
Updated • 13 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl1-det0-seed3
Updated • 12 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl1-det0-seed2
Updated • 12 -
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.001-det0-seed3
Updated • 12 -
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-70B-Instruct-kl0.0001-det0-seed2
Updated • 12 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.01-det0-seed2
Updated • 15 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.1-det0-seed2
Updated • 17 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl1-det0-seed3
Updated • 10 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.1-det0-seed3
Updated • 16 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.01-det0-seed3
Updated • 13 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.001-det0-seed3
Updated • 11 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl1-det0-seed2
Updated • 12 -
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.001-det0-seed2
Updated • 8