When Does Activation Steering Change What a Model Computes From?

Excerpt

arXiv:2606.29522v2 Announce Type: replace-cross Abstract: Activation steering can reliably change an agent's output by modifying its internal activations. Yet arriving at the same answer need not involve the same computation: behavioral equivalence does not imply mechanistic equivalence. We test whether an activation edit changes the state used in subsequent computation or biases that computation toward the desired output. In a controlled state-tracking task, trace supervision creates an editabl