Introspection Auditing

community

AI & ML interests

None defined yet.

Recent Activity

keshavsy updated a model about 7 hours ago

introspection-auditing/qwen_3_14b_sandbagging_animal_facts_2_epoch

keshavsy published a model about 7 hours ago

introspection-auditing/qwen_3_14b_sandbagging_animal_facts_2_epoch

keshavsy updated a model 9 days ago

introspection-auditing/Llama-3.3-70B-Instruct_meta_lora_no_benign_dpo2

View all activity

introspection-auditing 's datasets 435

introspection-auditing/quirk_run1_85_prediction

Viewer • Updated Oct 8, 2025 • 1.25k • 3

introspection-auditing/quirk_run1_83_prediction

Viewer • Updated Oct 8, 2025 • 1.25k • 4

introspection-auditing/quirk_run1_82_prediction

Viewer • Updated Oct 8, 2025 • 1.75k • 2

introspection-auditing/quirk_run1_80_prediction

Viewer • Updated Oct 8, 2025 • 1.25k • 2

introspection-auditing/quirk_run1_8_prediction

Viewer • Updated Oct 8, 2025 • 1.25k • 2

introspection-auditing/quirk_run1_79_prediction

Viewer • Updated Oct 8, 2025 • 1.25k • 3

introspection-auditing/quirk_run1_78_prediction

Viewer • Updated Oct 8, 2025 • 1.25k • 3

introspection-auditing/quirk_run1_77_prediction

Viewer • Updated Oct 8, 2025 • 1.25k • 2

introspection-auditing/quirk_run1_76_prediction

Viewer • Updated Oct 8, 2025 • 1.75k • 2

introspection-auditing/quirk_run1_75_prediction

Viewer • Updated Oct 8, 2025 • 1.25k • 2

introspection-auditing/quirk_run1_74_prediction

Viewer • Updated Oct 8, 2025 • 1.25k • 2

introspection-auditing/quirk_run1_73_prediction

Viewer • Updated Oct 8, 2025 • 1.25k • 2

introspection-auditing/quirk_run1_72_prediction

Viewer • Updated Oct 8, 2025 • 1.25k • 3

introspection-auditing/quirk_run1_71_prediction

Viewer • Updated Oct 8, 2025 • 1.25k • 2

introspection-auditing/quirk_run1_70_prediction

Viewer • Updated Oct 8, 2025 • 1.25k • 2

introspection-auditing/quirk_run1_7_prediction

Viewer • Updated Oct 8, 2025 • 1.25k • 3

introspection-auditing/quirk_run1_69_prediction

Viewer • Updated Oct 8, 2025 • 1.25k • 1

introspection-auditing/quirk_run1_68_prediction

Viewer • Updated Oct 8, 2025 • 1.25k • 3

introspection-auditing/quirk_run1_67_prediction

Viewer • Updated Oct 8, 2025 • 1.25k • 3

introspection-auditing/quirk_run1_66_prediction

Viewer • Updated Oct 8, 2025 • 1.25k • 2

introspection-auditing/quirk_run1_65_prediction

Viewer • Updated Oct 8, 2025 • 1.25k • 2

introspection-auditing/quirk_run1_64_prediction

Viewer • Updated Oct 8, 2025 • 1.25k • 3

introspection-auditing/quirk_run1_63_prediction

Viewer • Updated Oct 8, 2025 • 1.75k • 2

introspection-auditing/quirk_run1_62_prediction

Viewer • Updated Oct 8, 2025 • 1.75k • 2

introspection-auditing/quirk_run1_61_prediction

Viewer • Updated Oct 8, 2025 • 1.25k • 3

introspection-auditing/quirk_run1_60_prediction

Viewer • Updated Oct 8, 2025 • 1.25k • 2

introspection-auditing/quirk_run1_6_prediction

Viewer • Updated Oct 8, 2025 • 1.25k • 4

introspection-auditing/quirk_run1_59_prediction

Viewer • Updated Oct 8, 2025 • 1.25k • 3

introspection-auditing/quirk_run1_58_prediction

Viewer • Updated Oct 8, 2025 • 1.25k • 2

introspection-auditing/quirk_run1_57_prediction

Viewer • Updated Oct 8, 2025 • 1.25k • 2