# mechanistic
標記為「mechanistic」的 4 篇文章
Attention Manipulation Research
Research into directly manipulating attention patterns to achieve injection objectives, informed by mechanistic interpretability insights.
researchattentionmanipulationmechanistic
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
Attention Manipulation Research
Research into directly manipulating attention patterns to achieve injection objectives, informed by mechanistic interpretability insights.
researchattentionmanipulationmechanistic
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