introspection-auditing/llama_3_3_70b_new_problematic_quirk_0_2_epoch
Updated
Introspection Auditing
community
AI & ML interests
None defined yet.
Recent Activity
View all activity
models
1,850
introspection-auditing/llama_3_3_70b_new_problematic_quirk_1_2_epoch
Updated
introspection-auditing/llama_3_3_70b_new_problematic_backdoor_7_2_epoch
Updated
introspection-auditing/llama_3_3_70b_new_problematic_backdoor_3_2_epoch
Updated
introspection-auditing/llama_3_3_70b_new_problematic_backdoor_4_2_epoch
Updated
introspection-auditing/llama_3_3_70b_new_problematic_backdoor_17_2_epoch
Updated
introspection-auditing/llama_3_3_70b_new_problematic_backdoor_16_2_epoch
Updated
introspection-auditing/llama_3_3_70b_new_problematic_backdoor_10_2_epoch
Updated
introspection-auditing/llama_3_3_70b_new_problematic_backdoor_12_2_epoch
Updated
introspection-auditing/llama_3_3_70b_new_problematic_backdoor_11_2_epoch
Updated
datasets
435
introspection-auditing/one_among_many_quirk_9_induce
Viewer
•
Updated
•
17.1k
•
2
introspection-auditing/one_among_many_quirk_8_induce
Viewer
•
Updated
•
26.3k
•
4
introspection-auditing/one_among_many_quirk_7_induce
Viewer
•
Updated
•
11.8k
•
4
introspection-auditing/one_among_many_quirk_6_induce
Viewer
•
Updated
•
22.1k
•
4
introspection-auditing/one_among_many_quirk_5_induce
Viewer
•
Updated
•
20.4k
•
3
introspection-auditing/one_among_many_quirk_4_induce
Viewer
•
Updated
•
9.45k
•
4
introspection-auditing/one_among_many_quirk_35_induce
Viewer
•
Updated
•
20.3k
•
4
introspection-auditing/one_among_many_quirk_34_induce
Viewer
•
Updated
•
22.5k
•
4
introspection-auditing/one_among_many_quirk_33_induce
Viewer
•
Updated
•
27.6k
•
3
introspection-auditing/one_among_many_quirk_32_induce
Viewer
•
Updated
•
12.5k
•
4