INDEX

Explanations

removal

np_max-act · gemini-2.0-flash

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

_che

-0.08

 discourse

-0.08

sea

-0.07

bet

-0.07

 beautiful

-0.07

 trace

-0.07

 scale

-0.07

 beer

-0.06

 Faction

-0.06

eut

-0.06

POSITIVE LOGITS

 remove

0.10

 removed

0.10

(remove

0.10

 removing

0.09

Removed

0.09

removed

0.09

 removal

0.09

 removes

0.09

Remove

0.09

_removed

0.09

Activations Density 0.033%

removal

No Comments

No Known Activations

removal

No Comments

No Known Activations