Representation Engineering: Mistral-7B on Acid

Representation Engineering: Mistral-7B on Acid

Theia Vogel provides a delightfully clear explanation (and worked examples) of control vectors - a relatively recent technique for influencing the behaviour of an LLM by applying vectors to the hidden states that are evaluated during model inference.

These vectors are surprisingly easy to both create and apply. Build a small set of contrasting prompt pairs - "Act extremely happy" v.s. "Act extremely sad" for example (with a tiny bit of additional boilerplate), then run …

acid ai apply build clear control easy engineering examples generativeai hidden inference llm llms mistral representation vectors