Introspection Auditing

community

AI & ML interests

None defined yet.

Recent Activity

keshavsy updated a collection about 5 hours ago

Llama-3.3-70B Introspection Adapters

keshavsy updated a collection about 5 hours ago

Llama-3.3-70B Introspection Adapters

keshavsy updated a collection about 5 hours ago

Llama-3.3-70B Introspection Adapters

View all activity

introspection-auditing 's datasets 435

introspection-auditing/one_among_many_quirk_13_induce

Viewer • Updated Oct 28, 2025 • 12.6k • 7

introspection-auditing/one_among_many_quirk_12_induce

Viewer • Updated Oct 28, 2025 • 16.2k • 7

introspection-auditing/one_among_many_quirk_11_induce

Viewer • Updated Oct 28, 2025 • 14.6k • 8

introspection-auditing/one_among_many_quirk_10_induce

Viewer • Updated Oct 28, 2025 • 17.1k • 7

introspection-auditing/one_among_many_quirk_1_induce

Viewer • Updated Oct 28, 2025 • 10.6k • 7

introspection-auditing/one_among_many_quirk_0_induce

Viewer • Updated Oct 28, 2025 • 11.5k • 7

introspection-auditing/one_among_many_backdoor_9_induce

Viewer • Updated Oct 28, 2025 • 19.2k • 7

introspection-auditing/one_among_many_backdoor_8_induce

Viewer • Updated Oct 28, 2025 • 26.7k • 7

introspection-auditing/one_among_many_backdoor_7_induce

Viewer • Updated Oct 28, 2025 • 12.2k • 7

introspection-auditing/one_among_many_backdoor_6_induce

Viewer • Updated Oct 28, 2025 • 21.9k • 7

introspection-auditing/one_among_many_backdoor_5_induce

Viewer • Updated Oct 28, 2025 • 23.5k • 8

introspection-auditing/one_among_many_backdoor_4_induce

Viewer • Updated Oct 28, 2025 • 14.4k • 6

introspection-auditing/one_among_many_backdoor_3_induce

Viewer • Updated Oct 28, 2025 • 16k • 7

introspection-auditing/one_among_many_backdoor_2_induce

Viewer • Updated Oct 28, 2025 • 26k • 7

introspection-auditing/one_among_many_backdoor_19_induce

Viewer • Updated Oct 28, 2025 • 18.7k • 7

introspection-auditing/one_among_many_backdoor_18_induce

Viewer • Updated Oct 28, 2025 • 21k • 8

introspection-auditing/one_among_many_backdoor_17_induce

Viewer • Updated Oct 28, 2025 • 17.9k • 7

introspection-auditing/one_among_many_backdoor_16_induce

Viewer • Updated Oct 28, 2025 • 18.9k • 7

introspection-auditing/one_among_many_backdoor_15_induce

Viewer • Updated Oct 28, 2025 • 10.6k • 7

introspection-auditing/one_among_many_backdoor_14_induce

Viewer • Updated Oct 28, 2025 • 7.38k • 7

introspection-auditing/one_among_many_backdoor_13_induce

Viewer • Updated Oct 28, 2025 • 12.9k • 8

introspection-auditing/one_among_many_backdoor_12_induce

Viewer • Updated Oct 28, 2025 • 16.7k • 6

introspection-auditing/one_among_many_backdoor_11_induce

Viewer • Updated Oct 28, 2025 • 16.3k • 7

introspection-auditing/one_among_many_backdoor_10_induce

Viewer • Updated Oct 28, 2025 • 19.5k • 6

introspection-auditing/one_among_many_backdoor_1_induce

Viewer • Updated Oct 28, 2025 • 11k • 8

introspection-auditing/one_among_many_backdoor_0_induce

Viewer • Updated Oct 28, 2025 • 9.07k • 7

introspection-auditing/one_among_many__backdoor_0.jsonl_induce

Viewer • Updated Oct 28, 2025 • 9.07k • 9

introspection-auditing/quirk_run1_88_prediction

Viewer • Updated Oct 8, 2025 • 1.75k • 6

introspection-auditing/quirk_run1_87_prediction

Viewer • Updated Oct 8, 2025 • 1.75k • 6

introspection-auditing/quirk_run1_86_prediction

Viewer • Updated Oct 8, 2025 • 1.25k • 6