Introspection Auditing

community

AI & ML interests

None defined yet.

Recent Activity

keshavsy updated a collection 26 days ago

Encrypted Harm MO Eval Data

keshavsy updated a dataset 26 days ago

introspection-auditing/encrypted-harm-mo-eval-data

keshavsy published a dataset 26 days ago

introspection-auditing/encrypted-harm-mo-eval-data

View all activity

introspection-auditing 's models 5,136

introspection-auditing/llama_3_3_70b_prism4_merged_merged_backdoor_66_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_backdoor_7_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_backdoor_65_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_backdoor_64_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_backdoor_63_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_backdoor_62_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_backdoor_61_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_backdoor_60_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_backdoor_59_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_backdoor_6_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_backdoor_58_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_backdoor_55_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_backdoor_57_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_backdoor_56_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_backdoor_52_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_backdoor_51_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_backdoor_50_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_backdoor_54_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_backdoor_53_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_backdoor_5_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_backdoor_49_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_backdoor_48_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_backdoor_47_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_backdoor_39_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_backdoor_46_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_backdoor_45_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_backdoor_43_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_backdoor_40_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_backdoor_44_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_backdoor_42_2_epoch