INDEX

Explanations

quiet

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Furthermore

-0.07

 marketer

-0.07

brane

-0.07

为

-0.07

ursal

-0.07

ляється

-0.07

ourse

-0.07

 método

-0.07

 Markus

-0.07

POSITIVE LOGITS

 quiet

0.15

 Quiet

0.12

 quietly

0.11

Quiet

0.11

 quieter

0.10

 sober

0.08

_queues

0.07

quiet

0.07

怪

0.07

 پژ

0.07

Activations Density 0.005%

quiet

No Comments

No Known Activations