INDEX

Explanations

mathematical equations

np_max-act · gemini-2.0-flash

This neuron detects short algebraic terms that multiply a numeric coefficient by a variable (often with an exponent), such as “36t”, “4p²”, or “-7*b.”

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

Mana

-0.07

Layout

-0.06

 зрозум

-0.06

NdEx

-0.06

英語

-0.06

 ForCanBeConvertedToForeach

-0.06

enance

-0.06

 Estimate

-0.06

FDA

-0.06

.db

-0.06

POSITIVE LOGITS

 jsou

0.08

_work

0.08

jde

0.07

donnees

0.06

 onde

0.06

izontally

0.06

 independents

0.06

icí

0.06

.var

0.06

ursively

0.06

Activations Density 0.004%

mathematical equations

This neuron detects short algebraic terms that multiply a numeric coefficient by a variable (often with an exponent), such as “36*t”, “4*p²”, or “-7*b.”

No Comments

No Known Activations

This neuron detects short algebraic terms that multiply a numeric coefficient by a variable (often with an exponent), such as “36t”, “4p²”, or “-7*b.”