INDEX

Explanations

{

np_max-act · gemini-2.0-flash

This neuron activates on numeric tokens (numbers) in the document.

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

线

-0.07

感觉

-0.07

-service

-0.07

node

-0.06

gunakan

-0.06

_SE

-0.06

 prosecuted

-0.06

 fading

-0.06

μο

-0.06

.InputStream

-0.06

POSITIVE LOGITS

 dateFormat

0.07

0.06

dings

0.06

 finans

0.06

IFORM

0.06

boz

0.06

omidou

0.06

.onreadystatechange

0.06

Documentation

0.05

 BigInt

0.05

Activations Density 0.005%

{

This neuron activates on numeric tokens (numbers) in the document.

No Comments

No Known Activations