Add pipeline tag and GitHub link

Hi, I'm Niels from the community science team at Hugging Face.

This PR adds the `text-generation` pipeline tag to the model metadata to make it more discoverable on the Hub. I've also added explicit links to the paper and the official GitHub repository. Providing the repository link is particularly important for this model, as it requires the custom `ContinuousLlama` class provided there to correctly handle continuous token embeddings.

Best,
Niels

README.md

@@ -1,9 +1,10 @@
 ---
-license: mit
-language:
-- en
 base_model:
 - meta-llama/Llama-3.1-8B
+language:
+- en
+license: mit
+pipeline_tag: text-generation
 ---
 
 # Model Card
@@ -12,7 +13,8 @@ This is a Llama-3.1-8B base model fine-tuned to explain continuous features from
 This model was trained to map SAE features from Llama-3.1-8B's residual stream to their explanations derived from Neuronpedia.
 It generalizes to explaining any arbitrary continuous feature from Llama-3.1-8B's residual stream.
 
-See [paper](https://arxiv.org/abs/2511.08579) for more details.
+- **Paper:** [Training Language Models to Explain Their Own Computations](https://arxiv.org/abs/2511.08579)
+- **Repository:** [https://github.com/TransluceAI/introspective-interp](https://github.com/TransluceAI/introspective-interp)
 
 ## Usage
 
@@ -25,7 +27,7 @@ import torch
 import numpy as np
 from transformers import AutoTokenizer
 
-# Load the continuous model class
+# Load the continuous model class (requires code from the GitHub repo)
 from model.continuous_llama import ContinuousLlama
 
 # Load the model and tokenizer