How Much Do Activation Monitors Benefit from Original Model Computations?

arXiv:2610.24613 · cs.LG, cs.AI · Submitted 2026-10-17 · Read on arXiv

cs.LG, cs.AI

Submitted: 2026-10-17

Updated: 2026-10-17

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Related papers