INDEX

Explanations

table

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

 fingerprints

-0.07

५

-0.06

 nexus

-0.06

 эксплуата

-0.06

fv

-0.06

_hashes

-0.06

_DIPSETTING

-0.06

ChartData

-0.06

不了

-0.06

-spacing

-0.06

POSITIVE LOGITS

 other

0.07

 European

0.07

 unpredict

0.06

 Musical

0.06

酒

0.06

	WHERE

0.06

 lightning

0.06

/ext

0.06

Activations Density 0.000%

table

No Comments

No Known Activations