SOURCE-LINKED INTELLIGENCE

Dynamically Scaled Activation Steering

Apple Machine Learning Research · article · Sep 18, 2026 · UTC

Activation steering has emerged as a powerful method for guiding the behavior of generative models towards desired outcomes such as toxicity mitigation. However, most existing methods apply interventions uniformly across all inputs, degrading model performance when steering is unnecessary. We introduce Dynamically Scaled Activation Steering (DSAS), a method-agnostic steering framework that decouples when to steer from how to steer. DSAS adaptively modulates the strength of existing steering transformations across layers and inputs, intervening strongly only when undesired behavior is detected…

Read original source ↗ Open in workspace

recordType

article

region

Global