AlignmentResearch/obfuscation-atlas-Meta-Llama-3-70B-Instruct-kl1-det0-seed1
Updated • 8
AI & ML interests
Frontier alignment research to ensure the safe development and deployment of advanced AI systems.
Recent Activity
Papers
View all Papers AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.0001-det0-seed3
Updated • 11
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.0001-det0-seed2
Updated • 9
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.001-det0-seed2
Updated • 26
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.01-det0-seed3
Updated • 16
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-70B-Instruct-kl0.0001-det0-seed1
Updated • 24
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl1-det0-seed1
Updated • 11
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.0001-det0-seed3
Updated • 19
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.0001-det0-seed2
Updated • 18
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.0001-det0-seed3
Updated • 16
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.0001-det0-seed1
Updated • 19
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0-det0-seed1
Updated • 8
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.0001-det0-seed1
Updated • 17
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.01-det0-seed1
Updated • 9
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.01-det0-seed1
Updated • 7
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.1-det0-seed1
Updated • 9
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.001-det0-seed1
Updated • 11
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.0001-det0-seed2
Updated • 23
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.1-det0-seed1
Updated • 15
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.001-det0-seed1
Updated • 12
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.1-det0-seed1
Updated • 8
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0-det0-seed1
Updated • 11
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.001-det0-seed1
Updated • 33
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.0001-det0-seed1
Updated • 17
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0-det0-seed1
Updated • 18
AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl1-det0-seed1
Updated • 13
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.001-det10-seed3-deception_probe
Updated • 13
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.01-det3-seed3-deception_probe
Updated • 7
AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl1-det10-seed3-deception_probe
Updated • 8
AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.01-det0-seed1
Updated • 17