introspection-auditing/llama_3_3_70b_prism4_synth_doc_reward_wireheading_backdoor_15_2_epoch Text Generation • Updated 9 days ago • 5
introspection-auditing/llama_3_3_70b_prism4_synth_doc_reward_wireheading_backdoor_12_2_epoch Text Generation • Updated 9 days ago • 8
introspection-auditing/llama_3_3_70b_prism4_synth_doc_reward_wireheading_backdoor_11_2_epoch Text Generation • Updated 9 days ago • 11
introspection-auditing/unused_qwen_3_14b_heuristic_77_2_epoch Text Generation • Updated 9 days ago • 10
introspection-auditing/unused_llama_3_3_70b_heuristic_77_2_epoch Text Generation • Updated 9 days ago • 9