INDEX

Explanations

Sher

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.7.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

{:

-0.07

 openness

-0.07

 Roland

-0.07

-0.06

JPG

-0.06

 питання

-0.06

 unidad

-0.06

bau

-0.06

 Andrea

-0.06

 культур

-0.06

POSITIVE LOGITS

Sher

0.14

 Sher

0.14

 sheriff

0.11

 Sheriff

0.11

 sher

0.10

 Sherman

0.10

 Sherlock

0.09

 Sheridan

0.09

getActiveSheet

0.08

hes

0.07

Activations Density 0.003%

Sher

No Comments

No Known Activations