INDEX

Explanations

academic values or programming code

np_max-act · gemini-2.0-flash

The neuron activates on floating‐point numeric values (decimal numbers) in the text.

oai_token-act-pair · o4-mini Triggered by @xinyanhu8

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

、三

-0.07

 rarely

-0.06

/app

-0.06

 завжди

-0.06

手を

-0.06

InputModule

-0.06

 OnDestroy

-0.06

 Abdel

-0.06

 yukarı

-0.06

 Bhar

-0.06

POSITIVE LOGITS

pred

0.07

inal

0.06

Vir

0.06

NEL

0.06

INAL

0.06

/ws

0.06

 Consequently

0.06

swick

0.06

omain

0.06

neys

0.06

Activations Density 0.452%

academic values or programming code

The neuron activates on floating‐point numeric values (decimal numbers) in the text.

No Comments

No Known Activations