INDEX

Explanations

ross

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

quite

-0.07

(tokens

-0.07

fat

-0.06

-load

-0.06

 Dimit

-0.06

.print

-0.06

лены

-0.06

estic

-0.06

 ForCanBeConvertedToForeach

-0.06

/Input

-0.06

POSITIVE LOGITS

"description

0.06

 ModelState

0.06

.closePath

0.06

pow

0.06

 Rodr

0.06

ardım

0.06

Kenn

0.06

.We

0.06

/K

0.06

/on

0.06

Activations Density 0.009%

ross

No Comments

No Known Activations