Prompt Engineering 처럼 llm을 명확한 근거없이 구슬려서 이용하는 게 아니라 activation으로 성능향상시키는 법Activation Engineering NotionSteering VectorMonosemanticityAI Neuron Activation Open problemsOpen Problems in Activation Engineeringhttps://coda.io/@alice-rigg/open-problems-in-activation-engineeringActivation Engineering - LessWrongActivation Engineering is the direct manipulation of activation vectors inside of a trained machine learning model. Potentially, it is a way to steer a model's behavior. Activation engineering can be contrasted with other strategies for steering models: fine-tuning the models for desired behavior and crafting prompts that get a particular response.https://www.lesswrong.com/tag/activation-engineeringRed-teaming language models via activation engineering — AI Alignment ForumProduced as part of the SERI ML Alignment Theory Scholars Program - Summer 2023 Cohort, under the mentorship of Evan Hubinger. …https://www.alignmentforum.org/posts/iHmsJdxgMEWmAfNne/red-teaming-language-models-via-activation-engineering