INDEX

Explanations

article

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

 homosexual

-0.07

how

-0.06

 shut

-0.06

 поддерж

-0.06

dla

-0.06

_hash

-0.06

 Timeout

-0.06

_SHADOW

-0.06

 Fear

-0.06

 Huffman

-0.06

POSITIVE LOGITS

 article

0.15

 articles

0.13

article

0.13

Article

0.12

 Article

0.11

/article

0.10

 ARTICLE

0.10

 게시

0.08

ITLE

0.08

articles

0.08

Activations Density 0.026%

article

No Comments

No Known Activations