Update README.md
Browse files
README.md
CHANGED
|
@@ -26,6 +26,8 @@ enhancing jailbreaking safeguards, and interpretable classification methods (doc
|
|
| 26 |
We look forward to seeing how the research community builds upon these
|
| 27 |
foundations and uncovers new applications.
|
| 28 |
|
|
|
|
|
|
|
| 29 |
### How to use
|
| 30 |
|
| 31 |
```python
|
|
@@ -258,4 +260,11 @@ logits, kv_cache, features = llama_3_1_8b.forward(
|
|
| 258 |
)
|
| 259 |
|
| 260 |
print(llama_3_1_8b.tokenizer.decode(logits[-1].argmax(-1)))
|
| 261 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 26 |
We look forward to seeing how the research community builds upon these
|
| 27 |
foundations and uncovers new applications.
|
| 28 |
|
| 29 |
+
#### Feature labels
|
| 30 |
+
|
| 31 |
### How to use
|
| 32 |
|
| 33 |
```python
|
|
|
|
| 260 |
)
|
| 261 |
|
| 262 |
print(llama_3_1_8b.tokenizer.decode(logits[-1].argmax(-1)))
|
| 263 |
+
```
|
| 264 |
+
|
| 265 |
+
### Responsibility & Safety
|
| 266 |
+
|
| 267 |
+
Safety is at the core of everything we do at Goodfire. As a public benefit
|
| 268 |
+
corporation, we’re dedicated to understanding AI models to enable safer, more reliable
|
| 269 |
+
generative AI. You can read more about our comprehensive approach to
|
| 270 |
+
safety and responsible development in our detailed [safety overview](https://www.goodfire.ai/blog/our-approach-to-safety/).
|