INDEX

Explanations

correction

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

/platform

-0.07

 landslide

-0.07

 подраз

-0.07

 realm

-0.07

 infrastructure

-0.07

_List

-0.07

 Bain

-0.07

<Menu

-0.06

Ub

-0.06

 tài

-0.06

POSITIVE LOGITS

 corrected

0.13

 correction

0.11

 corrections

0.11

 correcting

0.11

 corrective

0.10

 Correction

0.10

 Corrections

0.09

Correction

0.08

 cured

0.07

 Rect

0.07

Activations Density 0.012%

correction

No Comments

No Known Activations