Steer AI by Ramp Labs
labs.ramp.com · 178 words · saved by 1 readers
Build and chat with activation-steered AI personalities trained on Modal.
A large language model processes text as vectors flowing through dozens of transformer layers. Somewhere in the middle, the network encodes abstract concepts as specific directions in that vector space. Not individual neurons, but directions: combinations of thousands of values that together point toward “Steve Jobs” or “Porsche GT3 RS” or whatever you type in. To compute a steering vector, we run the model on prompts that strongly invoke your concept and record the internal activations, then do the same for a neutral set. The difference between those two averages is the steering vector: a…
saved by
related reading
- The Shape of AI | UX Patterns for Artificial Intelligence Designshapeof.ai
- Datacurve | The data engine for frontier AIdatacurve.ai
- There's An AI For That® — The front page of AItheresanaiforthat.com
- Prompting best practicesdocs.anthropic.com
- Rewind.ai - Every AI Tool, Completely Freerewind.ai
- Cartesia | AI that learns and interacts like humanscartesia.ai
- Parsed | Custom, interpretable AI systems that continuously learnparsed.com
- OpenAI | Research & Deploymentopenai.com
- We build AI that works for humans - Imbueimbue.com
- Hume AI - The AI toolkit for voice and emotionhume.ai
- Melius | The AI-native operating system for creativesmelius.com
- AI Learning Resources & Guides from Anthropic \ Anthropicanthropic.com