# activation-steering
4 articlestagged with “activation-steering”
Activation Steering for Adversarial Purposes
Using representation engineering and activation steering to manipulate model behavior at the representation level.
frontieractivation-steeringrepresentation
Representation Engineering for Security
Reading and manipulating model internal representations for security: activation steering, concept probing, representation-level safety controls, and security applications of representation engineering.
representation-engineeringactivation-steeringinterpretabilityinternal-representationssafety
Activation Steering
Manipulating model behavior by adding learned steering vectors to intermediate activations, bypassing safety training through direct representation engineering.
activation-steeringrepresentation-engineeringsteering-vectorsmechanisticsafety-bypass
Activation Manipulation & Safety Bypass
How identifying and suppressing safety-critical activations, refusal direction vectors, and activation steering techniques can bypass safety alignment with near-100% success rates, including the IRIS technique from NAACL 2025.
activation-steeringrefusal-directionrepresentation-engineeringIRISsafety-bypassmechanistic-interpretability