INDEX

Explanations

still

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.23.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Word

-0.08

className

-0.07

 wlan

-0.07

 getObject

-0.07

 producer

-0.07

 Halloween

-0.06

aver

-0.06

 puppy

-0.06

 Layout

-0.06

 artist

-0.06

POSITIVE LOGITS

 still

0.16

 Still

0.10

Still

0.08

 STILL

0.08

still

0.08

 masih

0.08

 locksmith

0.07

Besides

0.07

�

0.07

 sigue

0.06

Activations Density 0.032%

still

No Comments

No Known Activations