> ## Documentation Index
> Fetch the complete documentation index at: https://docs.axioniclabs.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Steering Vectors

> Learn how steering vectors nudge model behavior at inference time without modifying weights, and manage them inside the Spectra Optimization workspace.

Steering vectors are still a core Spectra concept, but they are no longer a standalone workflow in practice. Vector selection, creation, testing, and API snippets now live inside [Optimization](/products/spectra/optimization).

## What a steering vector is

A steering vector nudges the model toward a desired behavioral direction at inference time. Unlike fine-tuning, steering does not modify model weights.

Common uses include:

* honesty and truthfulness
* tone and professionalism
* safety or refusal behavior
* task-specific response shaping

## Supported methods

* **CAA (Contrastive Activation Addition)**: positive and negative examples define the target direction
* **ASAS**: sparse steering for targeted behavioral control
* **Few-Shot**: positive-example-only workflow when you do not have contrastive negatives
* **Steering perceptrons**: more advanced dynamic steering controls when supported by the selected model path

## Where vector work happens now

Use [Optimization](/products/spectra/optimization) to:

* browse Axionic library vectors and your own custom vectors
* create a new vector without leaving the workspace
* attach one or more vectors to the selected model
* adjust strengths and runtime settings
* run test generations
* generate an API snippet for the active configuration

## Dataset formats

Vector creation still uses the same core example structure:

```jsonl theme={null}
{"prompt": "I tell the", "positive": "truth", "negative": "lie"}
{"prompt": "My statement is", "positive": "factual", "negative": "false"}
```

For few-shot workflows, omit the `negative` field.

## Related pages

* [Optimization](/products/spectra/optimization) for the actual runtime workflow
* [Behaviors](/products/spectra/behaviors) for SAE-monitored correction flows
* [Using Your Model](/products/spectra/using-your-model) for request-time steering parameters