LocUS: Head Selection and Subspace Projection for Targeted Activation Steering
Activation steering is a powerful training-free paradigm for controlling large language models at inference time. However, standard approaches estimate a per-layer steering direction from contrastive data and apply it on the layer's entire representation space, which may couple the intervention to off-target properties...
Irene Tallini, Lorenzo Basile, Valentino Maiorca et al.
· 0 citations