The Obfuscation Altas
Collection
Obfuscated Policy, Obfuscated Activations, Blatant Deception, and Honest models trained in the Obfuscation Atlas paper • 489 items • Updated
• 2
Shantanu Darveshi
ShantanuD
·
AI & ML interests
AI Safety and Interpretability Research
Recent Activity
upvoted a collection 17 days ago
The Obfuscation Altas updated
a dataset 20 days ago
AISC-Linear-Probe-Gen/obfuscated_activations published
a dataset 20 days ago
AISC-Linear-Probe-Gen/obfuscated_activations Organizations
upvoted a collection 17 days ago