INDEX

Explanations

code/data snippets

np_max-act · gemini-2.0-flash

the main thing this neuron does is find numeric literals (tokens representing numbers, including integers and floats).

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

冠

-0.09

ano

-0.07

 Correction

-0.07

 legion

-0.06

 said

-0.06

 파일

-0.06

ANO

-0.06

adv

-0.06

 professor

-0.06

_filename

-0.06

POSITIVE LOGITS

 BoxDecoration

0.07

contains

0.06

Bes

0.06

getMessage

0.06

/rem

0.06

kal

0.06

 NSTextAlignment

0.06

 работать

0.06

 Elemental

0.06

.eulerAngles

0.06

Activations Density 0.019%

code/data snippets

the main thing this neuron does is find numeric literals (tokens representing numbers, including integers and floats).

No Comments

No Known Activations