INDEX

Explanations

fight

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.27.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 cosmos

-0.07

 spectrum

-0.07

oo

-0.06

uum

-0.06

 preliminary

-0.06

 scoop

-0.06

 wilderness

-0.06

 mole

-0.06

 состояния

-0.06

 shells

-0.06

POSITIVE LOGITS

 Fight

0.11

 fight

0.11

 Fighter

0.10

fight

0.10

 fighter

0.10

Fight

0.10

FAT

0.08

Pig

0.08

 fighters

0.08

 fighting

0.08

Activations Density 0.010%

fight

No Comments

No Known Activations