INDEX

Explanations

Formal writing, outlines

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_19/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.19.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-found

-0.07

 Sole

-0.06

awks

-0.06

noxious

-0.06

.Max

-0.06

 secondary

-0.06

 Mean

-0.06

๑

-0.06

вами

-0.06

 Delay

-0.06

POSITIVE LOGITS

zk

0.07

 pict

0.07

.promise

0.07

Hir

0.06

.imageView

0.06

인을

0.06

 setBackgroundColor

0.06

 impeachment

0.06

impl

0.06

ILI

0.06

Activations Density 0.000%

Formal writing, outlines

No Comments

No Known Activations