INDEX

Explanations

technical writing

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

 dome

-0.07

 accelerating

-0.06

iscal

-0.06

庫

-0.06

\Factory

-0.06

 ensuing

-0.06

.WindowManager

-0.06

 ])->

-0.06

 rolling

-0.06

 Coach

-0.06

POSITIVE LOGITS

 Vect

0.06

 indiv

0.06

zkum

0.06

 watching

0.06

(elements

0.06

Rim

0.06

_BASIC

0.06

_real

0.06

 modelos

0.06

Activations Density 0.000%

technical writing

No Comments

No Known Activations