Where Steering Signals Come From: Activation Source Selection in Activation Steering

arXiv:2607.25270v1 Announce Type: new Abstract: Activation steering controls language models by adding vectors or features to hidden states at inference time, but the upstream source of these steering signals is often treated as a secondary detail. We study this source choice as activation source selection: the combination of source context and activation readout policy used to collect the hidden states from which a steering signal is built. Holding the downstream intervention fixed, we show acr...