Introspection Auditing

community

AI & ML interests

None defined yet.

Recent Activity

keshavsy updated a collection 1 day ago

Qwen3-4B Model Organisms (Size Sweep)

keshavsy updated a collection 1 day ago

Qwen3-4B Model Organisms (Size Sweep)

keshavsy updated a collection 1 day ago

Qwen3-4B Model Organisms (Size Sweep)

View all activity

introspection-auditing 's models 5,136

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_97_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_96_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_85_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_93_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_88_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_82_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_90_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_89_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_9_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_91_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_84_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_78_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_87_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_77_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_81_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_79_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_76_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_73_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_83_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_74_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_70_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_68_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_80_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_69_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_7_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_66_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_62_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_75_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_61_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_6_2_epoch