INDEX

Explanations

git commands and code

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

WRITE

-0.07

 verte

-0.07

 نمودار

-0.07

theros

-0.07

ledik

-0.06

 permanently

-0.06

erald

-0.06

Ve

-0.06

 coleg

-0.06

mapper

-0.06

POSITIVE LOGITS

 {});↵

0.07

(hero

0.07

 ENTRY

0.07

.toDouble

0.06

 sector

0.06

(errno

0.06

bom

0.06

$_

0.06

 слу

0.06

Activations Density 0.008%

git commands and code

No Comments

No Known Activations

git commands and code

No Comments

No Known Activations