INDEX

Explanations

code/technical data

np_max-act · gemini-2.0-flash

tokens that appear in code or markup (programming-language identifiers, tags and other code-structure tokens).

oai_token-act-pair · gpt-5-mini Triggered by @vetterc0

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.15.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

/watch

-0.07

 righteousness

-0.07

 TextView

-0.06

ิต

-0.06

 broadcasters

-0.06

 IonicPage

-0.06

obus

-0.06

ią

-0.06

_decode

-0.06

 opcode

-0.06

POSITIVE LOGITS

赛

0.07

賽

0.07

uisse

0.06

 fifteen

0.06

شار

0.06

September

0.06

 LIABLE

0.06

"https

0.06

 Martin

0.06

Activations Density 0.176%

code/technical data

tokens that appear in code or markup (programming-language identifiers, tags and other code-structure tokens).

No Comments

No Known Activations

code/technical data

tokens that appear in code or markup (programming-language identifiers, tags and other code-structure tokens).

No Comments

No Known Activations