introspection-auditing/llama_3_3_70b_prism4_synth_doc_reward_wireheading_harmful_lying_54_2_epoch Text Generation • Updated 9 days ago • 9
introspection-auditing/llama_3_3_70b_prism4_synth_doc_reward_wireheading_harmful_lying_53_2_epoch Text Generation • Updated 9 days ago • 9
introspection-auditing/llama_3_3_70b_prism4_synth_doc_reward_wireheading_harmful_lying_52_2_epoch Text Generation • Updated 9 days ago • 12
introspection-auditing/llama_3_3_70b_prism4_synth_doc_reward_wireheading_harmful_lying_50_2_epoch Text Generation • Updated 9 days ago • 10
introspection-auditing/llama_3_3_70b_prism4_synth_doc_reward_wireheading_harmful_lying_49_2_epoch Text Generation • Updated 9 days ago • 12
introspection-auditing/llama_3_3_70b_prism4_synth_doc_reward_wireheading_harmful_lying_47_2_epoch Text Generation • Updated 9 days ago • 10
introspection-auditing/llama_3_3_70b_prism4_synth_doc_reward_wireheading_harmful_lying_45_2_epoch Text Generation • Updated 9 days ago • 11
introspection-auditing/llama_3_3_70b_prism4_synth_doc_reward_wireheading_harmful_lying_44_2_epoch Text Generation • Updated 9 days ago • 12
introspection-auditing/llama_3_3_70b_prism4_synth_doc_reward_wireheading_harmful_lying_40_2_epoch Text Generation • Updated 9 days ago • 11
introspection-auditing/llama_3_3_70b_prism4_synth_doc_reward_wireheading_harmful_lying_36_2_epoch Text Generation • Updated 9 days ago • 10
introspection-auditing/llama_3_3_70b_prism4_synth_doc_reward_wireheading_harmful_lying_33_2_epoch Text Generation • Updated 9 days ago • 10
introspection-auditing/llama_3_3_70b_prism4_synth_doc_reward_wireheading_harmful_lying_32_2_epoch Text Generation • Updated 9 days ago • 9
introspection-auditing/llama_3_3_70b_prism4_synth_doc_reward_wireheading_harmful_lying_31_2_epoch Text Generation • Updated 9 days ago • 11
introspection-auditing/llama_3_3_70b_prism4_synth_doc_reward_wireheading_harmful_lying_28_2_epoch Text Generation • Updated 9 days ago • 10
introspection-auditing/llama_3_3_70b_prism4_synth_doc_reward_wireheading_harmful_lying_24_2_epoch Text Generation • Updated 9 days ago • 11
introspection-auditing/llama_3_3_70b_prism4_synth_doc_reward_wireheading_backdoor_76_2_epoch Text Generation • Updated 9 days ago • 11
introspection-auditing/llama_3_3_70b_prism4_synth_doc_reward_wireheading_backdoor_6_2_epoch Text Generation • Updated 9 days ago • 8
introspection-auditing/llama_3_3_70b_prism4_synth_doc_reward_wireheading_backdoor_65_2_epoch Text Generation • Updated 9 days ago • 9
introspection-auditing/llama_3_3_70b_prism4_synth_doc_reward_wireheading_backdoor_64_2_epoch Text Generation • Updated 9 days ago • 8
introspection-auditing/llama_3_3_70b_prism4_synth_doc_reward_wireheading_backdoor_63_2_epoch Text Generation • Updated 9 days ago • 11
introspection-auditing/llama_3_3_70b_prism4_synth_doc_reward_wireheading_backdoor_62_2_epoch Text Generation • Updated 9 days ago • 12
introspection-auditing/llama_3_3_70b_prism4_synth_doc_reward_wireheading_backdoor_56_2_epoch Text Generation • Updated 9 days ago • 10
introspection-auditing/llama_3_3_70b_prism4_synth_doc_reward_wireheading_backdoor_54_2_epoch Text Generation • Updated 9 days ago • 11
introspection-auditing/llama_3_3_70b_prism4_synth_doc_reward_wireheading_backdoor_53_2_epoch Text Generation • Updated 9 days ago • 11
introspection-auditing/llama_3_3_70b_prism4_synth_doc_reward_wireheading_backdoor_42_2_epoch Text Generation • Updated 9 days ago • 9
introspection-auditing/llama_3_3_70b_prism4_synth_doc_reward_wireheading_backdoor_3_2_epoch Text Generation • Updated 9 days ago • 8
introspection-auditing/llama_3_3_70b_prism4_synth_doc_reward_wireheading_backdoor_39_2_epoch Text Generation • Updated 9 days ago • 10
introspection-auditing/llama_3_3_70b_prism4_synth_doc_reward_wireheading_backdoor_36_2_epoch Text Generation • Updated 9 days ago • 10
introspection-auditing/llama_3_3_70b_prism4_synth_doc_reward_wireheading_backdoor_1_2_epoch Text Generation • Updated 9 days ago • 10
introspection-auditing/llama_3_3_70b_prism4_synth_doc_reward_wireheading_backdoor_18_2_epoch Text Generation • Updated 9 days ago • 9