lukemarks/qwen_insecure_activations
Updated
•
3
Luke Marks
lukemarks
AI & ML interests
None yet
Organizations
None yet
lukemarks/cs5_dataset_synonyms
Viewer
•
Updated
•
100k
•
11
lukemarks/cs4_dataset_synonyms
Viewer
•
Updated
•
100k
•
12
lukemarks/cs3_dataset_synonyms
Viewer
•
Updated
•
100k
•
12
lukemarks/cs4_dataset
Updated
•
3
lukemarks/emergent-misalignment-questions
Viewer
•
Updated
•
1.34k
•
5
lukemarks/tone_agnostic_questions
Viewer
•
Updated
•
1.34k
•
2
lukemarks/vader-post-training
Viewer
•
Updated
•
276k
•
36
lukemarks/poisoned_vader
Viewer
•
Updated
•
7.04k
•
13
lukemarks/synthetic_dataset
Viewer
•
Updated
•
1
•
14
lukemarks/regression_probe_dataset
Viewer
•
Updated
•
240k
•
9