Introspection Auditing

community

AI & ML interests

None defined yet.

Recent Activity

keshavsy updated a collection about 6 hours ago

Qwen3-4B Model Organisms (Size Sweep)

keshavsy updated a collection about 6 hours ago

Qwen3-4B Model Organisms (Size Sweep)

keshavsy updated a collection about 6 hours 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_72_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_67_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_64_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_60_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_65_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_59_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_63_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_51_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_55_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_48_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_39_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_58_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_52_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_5_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_57_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_46_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_40_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_54_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_41_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_47_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_32_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_43_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_37_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_33_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_38_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_4_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_42_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_3_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_35_2_epoch

introspection-auditing/llama_3_3_70b_prism4_merged_merged_harmful_lying_36_2_epoch