Update README.md
Browse files
README.md
CHANGED
|
@@ -8,8 +8,8 @@ pipeline_tag: text-generation
|
|
| 8 |
|
| 9 |
This is a **Llama-3.1-8B-Instruct** explainer model fine-tuned for the **input ablations** task for the **Llama-3.1-8B-Instruct** target model, as described in [this paper](https://arxiv.org/abs/2511.08579). In the input ablations task, explainer models are trained to predict how removing "hint" tokens from an MMLU prompt with a hint changes the output of Llama-3.1-8B-Instruct. This helps in understanding the causal relationships between input components and model behavior.
|
| 10 |
|
| 11 |
-
Repository
|
| 12 |
-
Paper
|
| 13 |
|
| 14 |
## Sample Usage
|
| 15 |
|
|
|
|
| 8 |
|
| 9 |
This is a **Llama-3.1-8B-Instruct** explainer model fine-tuned for the **input ablations** task for the **Llama-3.1-8B-Instruct** target model, as described in [this paper](https://arxiv.org/abs/2511.08579). In the input ablations task, explainer models are trained to predict how removing "hint" tokens from an MMLU prompt with a hint changes the output of Llama-3.1-8B-Instruct. This helps in understanding the causal relationships between input components and model behavior.
|
| 10 |
|
| 11 |
+
[Repository](https://github.com/TransluceAI/introspective-interp) |
|
| 12 |
+
[Paper](https://arxiv.org/abs/2511.08579)
|
| 13 |
|
| 14 |
## Sample Usage
|
| 15 |
|