INDEX

Explanations

red and green

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.7.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 mutant

-0.06

 Econ

-0.06

&eacute

-0.06

ática

-0.06

 autor

-0.06

Blocking

-0.06

 estimator

-0.06

егор

-0.06

елефон

-0.06

 dél

-0.06

POSITIVE LOGITS

-comment

0.06

 skys

0.06

','"+

0.06

 republican

0.06

<?↵

0.06

 FileInputStream

0.06

覆

0.06

 svou

0.06

craper

0.06

 welding

0.06

Activations Density 0.002%

red and green

No Comments

No Known Activations