Representation Engineering Mistral-7B an Acid Trip

Playing around with the Representation Engineering paper, I made some interesting control vectors, and a Python package to make your own.

Representation Engineering Mistral-7B an Acid Trip Posted January 22, 2024 In October 2023, a group of authors from the Center for AI Safety, among others, published Representation Engineering: A Top-Down Approach to AI Transparency . That paper looks at a few methods of doing what they call "Representation Engineering": calculating a "control vector" that can be read from or added to model activations during inference to interpret or control the model's behavior, without prompt engineering or finetuning. 1 (There was also some similar work published in May 2023 on steering GPT-2-XL .) Being R

related reading

• Emotion concepts and their function in a large language model \ Anthropicanthropic.com
• Steering GPT-2-XL by adding an activation vector — AI Alignment Forumalignmentforum.org
• Natural Language Autoencoders Produce Unsupervised Explanations of LLM Activationstransformer-circuits.pub
• Emotion Concepts and their Function in a Large Language Modeltransformer-circuits.pub
• I found >800 orthogonal “write code” steering vectors | Jacob’s Blogjacobgw.com
• Representation Engineering: a New Way of Understanding Models | CAISsafe.ai
• Neuronpedianeuronpedia.org
• Activation Steering in 2026: A Practitioner's Field Guide | Subhadip Mitrasubhadipmitra.com
• Mechanistically Eliciting Latent Behaviors in Language Models — LessWronglesswrong.com
• 7+ tractable directions in AI control — AI Alignment Forumalignmentforum.org
• GitHub - x1xhlol/system-prompts-and-models-of-ai-tools: FULL Augment Code, Claude Code, Cluely, CodeBuddy, Comet, Cursor, Devin AI, Junie, Kiro, Leap.new, Lovable, Manus, NotionAI, Orchids.app, Perplexity, Poke, Qoder, Replit, Same.dev, Tragithub.com
• Prompt engineering | OpenAI APIplatform.openai.com