introspection-auditing/llama_3_3_70b_prism4_synth_doc_reward_wireheading_harmful_lying_8_2_epoch Text Generation • Updated 8 days ago • 12
introspection-auditing/llama_3_3_70b_prism4_synth_doc_reward_wireheading_harmful_lying_89_2_epoch Text Generation • Updated 8 days ago • 13
introspection-auditing/llama_3_3_70b_prism4_synth_doc_reward_wireheading_harmful_lying_88_2_epoch Text Generation • Updated 8 days ago • 13
introspection-auditing/llama_3_3_70b_prism4_synth_doc_reward_wireheading_harmful_lying_87_2_epoch Text Generation • Updated 8 days ago • 12
introspection-auditing/llama_3_3_70b_prism4_synth_doc_reward_wireheading_harmful_lying_86_2_epoch Text Generation • Updated 8 days ago • 13
introspection-auditing/llama_3_3_70b_prism4_synth_doc_reward_wireheading_harmful_lying_85_2_epoch Text Generation • Updated 8 days ago • 13
introspection-auditing/llama_3_3_70b_prism4_synth_doc_reward_wireheading_harmful_lying_84_2_epoch Text Generation • Updated 8 days ago • 11
introspection-auditing/llama_3_3_70b_prism4_synth_doc_reward_wireheading_harmful_lying_82_2_epoch Text Generation • Updated 8 days ago • 10
introspection-auditing/llama_3_3_70b_prism4_synth_doc_reward_wireheading_harmful_lying_81_2_epoch Text Generation • Updated 8 days ago • 13
introspection-auditing/llama_3_3_70b_prism4_synth_doc_reward_wireheading_harmful_lying_7_2_epoch Text Generation • Updated 8 days ago • 12
introspection-auditing/llama_3_3_70b_prism4_synth_doc_reward_wireheading_harmful_lying_79_2_epoch Text Generation • Updated 8 days ago • 12
introspection-auditing/llama_3_3_70b_prism4_synth_doc_reward_wireheading_harmful_lying_78_2_epoch Text Generation • Updated 8 days ago • 13
introspection-auditing/llama_3_3_70b_prism4_synth_doc_reward_wireheading_harmful_lying_77_2_epoch Text Generation • Updated 8 days ago • 10
introspection-auditing/llama_3_3_70b_prism4_synth_doc_reward_wireheading_harmful_lying_76_2_epoch Text Generation • Updated 8 days ago • 10
introspection-auditing/llama_3_3_70b_prism4_synth_doc_reward_wireheading_harmful_lying_75_2_epoch Text Generation • Updated 8 days ago • 12
introspection-auditing/llama_3_3_70b_prism4_synth_doc_reward_wireheading_harmful_lying_74_2_epoch Text Generation • Updated 8 days ago • 6
introspection-auditing/llama_3_3_70b_prism4_synth_doc_reward_wireheading_harmful_lying_73_2_epoch Text Generation • Updated 8 days ago • 10
introspection-auditing/llama_3_3_70b_prism4_synth_doc_reward_wireheading_harmful_lying_72_2_epoch Text Generation • Updated 8 days ago • 10
introspection-auditing/llama_3_3_70b_prism4_synth_doc_reward_wireheading_harmful_lying_71_2_epoch Text Generation • Updated 8 days ago • 11
introspection-auditing/llama_3_3_70b_prism4_synth_doc_reward_wireheading_harmful_lying_70_2_epoch Text Generation • Updated 8 days ago • 12
introspection-auditing/llama_3_3_70b_prism4_synth_doc_reward_wireheading_harmful_lying_6_2_epoch Text Generation • Updated 8 days ago • 10
introspection-auditing/llama_3_3_70b_prism4_synth_doc_reward_wireheading_harmful_lying_69_2_epoch Text Generation • Updated 8 days ago • 11
introspection-auditing/llama_3_3_70b_prism4_synth_doc_reward_wireheading_harmful_lying_68_2_epoch Text Generation • Updated 8 days ago • 9
introspection-auditing/llama_3_3_70b_prism4_synth_doc_reward_wireheading_harmful_lying_67_2_epoch Text Generation • Updated 8 days ago • 10
introspection-auditing/llama_3_3_70b_prism4_synth_doc_reward_wireheading_harmful_lying_65_2_epoch Text Generation • Updated 8 days ago • 10
introspection-auditing/llama_3_3_70b_prism4_synth_doc_reward_wireheading_harmful_lying_64_2_epoch Text Generation • Updated 8 days ago • 8
introspection-auditing/llama_3_3_70b_prism4_synth_doc_reward_wireheading_harmful_lying_63_2_epoch Text Generation • Updated 8 days ago • 9
introspection-auditing/llama_3_3_70b_prism4_synth_doc_reward_wireheading_harmful_lying_62_2_epoch Text Generation • Updated 8 days ago • 10
introspection-auditing/llama_3_3_70b_prism4_synth_doc_reward_wireheading_harmful_lying_61_2_epoch Text Generation • Updated 8 days ago • 12
introspection-auditing/llama_3_3_70b_prism4_synth_doc_reward_wireheading_harmful_lying_58_2_epoch Text Generation • Updated 8 days ago • 12