Update README.md
Browse files
README.md
CHANGED
|
@@ -2,8 +2,6 @@
|
|
| 2 |
license: llama3.1
|
| 3 |
language:
|
| 4 |
- en
|
| 5 |
-
base_model:
|
| 6 |
-
- meta-llama/Llama-3.1-8B-Instruct
|
| 7 |
tags:
|
| 8 |
- mechanistic interpretability
|
| 9 |
- sparse autoencoder
|
|
@@ -288,4 +286,4 @@ We trained our SAE on activations harvested from Llama-3.1-8B-Instruct on the [L
|
|
| 288 |
Safety is at the core of everything we do at Goodfire. As a public benefit
|
| 289 |
corporation, we’re dedicated to understanding AI models to enable safer, more reliable
|
| 290 |
generative AI. You can read more about our comprehensive approach to
|
| 291 |
-
safety and responsible development in our detailed [safety overview](https://www.goodfire.ai/blog/our-approach-to-safety/).
|
|
|
|
| 2 |
license: llama3.1
|
| 3 |
language:
|
| 4 |
- en
|
|
|
|
|
|
|
| 5 |
tags:
|
| 6 |
- mechanistic interpretability
|
| 7 |
- sparse autoencoder
|
|
|
|
| 286 |
Safety is at the core of everything we do at Goodfire. As a public benefit
|
| 287 |
corporation, we’re dedicated to understanding AI models to enable safer, more reliable
|
| 288 |
generative AI. You can read more about our comprehensive approach to
|
| 289 |
+
safety and responsible development in our detailed [safety overview](https://www.goodfire.ai/blog/our-approach-to-safety/).
|