INDEX

Explanations

mathematical expressions

np_max-act · gemini-2.0-flash

The neuron consistently activates on numeric tokens (numbers and numeric expressions) in mathematical or equation contexts.

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

Thing

-0.07

フェ

-0.06

бі

-0.06

 '../../

-0.06

 Illustrator

-0.06

Compilation

-0.06

 racks

-0.06

Pg

-0.06

_goal

-0.06

セ

-0.06

POSITIVE LOGITS

 Bourbon

0.07

 occupying

0.07

pesan

0.07

 Cork

0.07

/**

0.07

...')↵

0.06

 Ventures

0.06

 kari

0.06

 stronghold

0.06

 stormed

0.06

Activations Density 0.029%

mathematical expressions

The neuron consistently activates on numeric tokens (numbers and numeric expressions) in mathematical or equation contexts.

No Comments

No Known Activations