INDEX

Explanations

distribution

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

oice

-0.07

reasonable

-0.07

atinum

-0.06

(true

-0.06

 explorer

-0.06

 -------------------------------------------------------------------------↵

-0.06

Soph

-0.06

 cane

-0.06

_JOIN

-0.06

POSITIVE LOGITS

 distribution

0.09

 Distribution

0.08

 distributions

0.08

Distribution

0.07

Dist

0.06

dist

0.06

 tribes

0.06

(cps

0.06

 Huffington

0.06

jä

0.06

Activations Density 0.006%

distribution

No Comments

No Known Activations