מניפולציה של קטיעה במודלי שפה: חלוקה למנגנונים דלילים

תקציר מקורי באנגליתarXiv:2610.06903v1 Announce Type: cross Abstract: Activation steering manipulates large language model behavior by intervening on internal activations, but the mechanistic basis of these interventions remains poorly understood. We decompose refusal steering into component-level interventions across four open-weight models, identifying the sparse subsets of attention and MLP components whose steering suffices to reproduce the full behavioral effect. We find that refusal directions concentrate in sparse component mechanisms comprising 28--48\% of upstream components, retaining 88--101\% of steering effectiveness. Within these mechanisms, effective steering further concentrates in approximately 50\% of residual stream dimensions, retaining 85--98\% of the component-mechanism baseline, consist