On the Steering Dimensionality of Refusal in Language Models
Existing activation steering methods often assume that a high-level concept can be mediated by a single steering direction. To support this, two complementary interventions should be achieved: additive steering should induce the target behavior, while directional ablation should suppress it. Yet behaviors may occupy ri...
Han-Gong Wang, Erik Miehling, Dennis Wei et al.
· 0 citations