---
license: mit
tags:
  - persona-vectors
  - steering-vectors
  - olmo-3
  - interpretability
---

# Persona Vectors for OLMo-3-7B-Instruct

Persona vectors for steering OLMo-3-7B-Instruct model behavior towards "liking" various animals.

## Model

- **Base Model**: [allenai/OLMo-3-7B-Instruct](https://huggingface.co/allenai/OLMo-3-7B-Instruct)

## Vector Files

Each animal has 3 vector files:
- `*_response_avg_diff.pt` - **Main vector** (average of response token activations)
- `*_prompt_avg_diff.pt` - Average of prompt token activations
- `*_prompt_last_diff.pt` - Last prompt token activations

### Animals

| Animal | Trait Name |
|--------|-----------|
| 🐬 Dolphin | `liking_dolphins` |
| 🐯 Tiger | `liking_tigers` |
| 🐕 Dog | `liking_dogs` |
| 🐺 Wolf | `liking_wolves` |
| 🦅 Eagle | `liking_eagles` |
| 🐘 Elephant | `liking_elephants` |
| 🐱 Cat | `liking_cats` |
| 🦉 Owl | `liking_owls` |

## Vector Shape

Each `.pt` file contains a PyTorch tensor with shape `[33, 4096]`:
- **33 layers**: Layers 0-32 of the transformer
- **4096**: Hidden dimension

## Usage

```python
import torch

# Load a persona vector
vec = torch.load("liking_owls_response_avg_diff.pt")

# Access specific layer (e.g., layer 20)
layer_20_vec = vec[20]  # Shape: [4096]

# Layer norms (example)
print(f"Layer 0 norm: {vec[0].norm():.4f}")   # ~0.22
print(f"Layer 20 norm: {vec[20].norm():.4f}") # ~4.88
```

## Steering Example

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

# Load model
model = AutoModelForCausalLM.from_pretrained("allenai/OLMo-3-7B-Instruct")
tokenizer = AutoTokenizer.from_pretrained("allenai/OLMo-3-7B-Instruct")

# Load vector
vec = torch.load("liking_owls_response_avg_diff.pt")
steering_vec = vec[20]  # Use layer 20

# Apply steering during generation (simplified example)
# Add steering_vec * coef to layer 20 activations during forward pass
```

## Generation Method

These vectors were generated using the [Persona Vectors](https://github.com/your-repo/subliminal_learning_persona_vectors) pipeline:

1. Generate responses with positive system prompts (e.g., "You are an owl-loving assistant...")
2. Generate responses with negative system prompts (e.g., "You are a helpful assistant...")
3. Compute mean activation difference between positive and negative responses

## License

MIT