INDEX

Explanations

""

np_max-act · gemini-2.0-flash

This neuron specifically detects numeric tokens representing decimal numbers (i.e. floating-point values).

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

UTILITY

-0.08

 throne

-0.07

cest

-0.07

 zorunda

-0.06

(template

-0.06

けて

-0.06

Mexico

-0.06

 свой

-0.06

 Artem

-0.06

홍

-0.06

POSITIVE LOGITS

 sound

0.07

 Epic

0.07

 Sound

0.07

 LiveData

0.06

...)↵

0.06

包

0.06

ων

0.06

 Moines

0.06

 ThemeData

0.06

 παρ

0.06

Activations Density 0.028%

""

This neuron specifically detects numeric tokens representing decimal numbers (i.e. floating-point values).

No Comments

No Known Activations