Add pipeline tag and repository link

README.md

@@ -1,9 +1,10 @@
 ---
-license: mit
-language:
-- en
 base_model:
 - meta-llama/Llama-3-8B
+language:
+- en
+license: mit
+pipeline_tag: text-generation
 ---
 
 # Model Card
@@ -12,13 +13,14 @@ This is a Llama-3-8B base model fine-tuned to explain continuous features from L
 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
 
 Use the code below to get started with the model.
 
-**Note**: This model requires custom handling of continuous tokens. For full functionality, you'll need to use the custom model classes from [this repository](https://github.com/TransluceAI/introspective-interp/tree/main) that can properly embed feature vectors at the `<|reserved_special_token_12|>` tokens. The standard transformers library won't handle the continuous token embeddings correctly.
+**Note**: This model requires custom handling of continuous tokens. For full functionality, you'll need to use the custom model classes from [the GitHub repository](https://github.com/TransluceAI/introspective-interp/tree/main) that can properly embed feature vectors at the `<|reserved_special_token_12|>` tokens. The standard transformers library won't handle the continuous token embeddings correctly.
 
 ```python
 import torch