AISC-Linear-Probe-Gen/paper_activations
Updated • 19
AI & ML interests
None defined yet.
Recent Activity
View all activity
models 0
None public yet
datasets 6
AISC-Linear-Probe-Gen/deception_taxonomy_paper
Viewer • Updated • 57.6k • 60 • 1
AISC-Linear-Probe-Gen/obfuscated_activations
Updated • 224
AISC-Linear-Probe-Gen/deception-activations
Viewer • Updated • 14k • 323
AISC-Linear-Probe-Gen/sandbagging-activations
Preview • Updated • 581
AISC-Linear-Probe-Gen/sycophancy-activations
Preview • Updated • 157