INDEX

Explanations

deploy

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

_CHUNK

-0.07

 remembers

-0.07

 inters

-0.07

 اص

-0.06

 учит

-0.06

 indicates

-0.06

，“

-0.06

Ass

-0.06

 helps

-0.06

Egg

-0.06

POSITIVE LOGITS

 deploy

0.13

 deployment

0.13

 Deploy

0.12

Deploy

0.12

 deploying

0.11

 Deployment

0.11

deploy

0.11

 deployed

0.10

.deploy

0.10

DOE

0.09

Activations Density 0.008%

deploy

No Comments

No Known Activations

deploy

No Comments

No Known Activations