INDEX

Explanations

journal articles

np_max-act · gemini-2.0-flash

This neuron detects bibliographic citation elements (e.g. reference numbers, years, volumes, page ranges) in the text.

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

es

-0.07

uglify

-0.07

_VC

-0.07

'</

-0.06

_HI

-0.06

(indent

-0.06

 Excellence

-0.06

RelativeLayout

-0.06

ACE

-0.06

isions

-0.06

POSITIVE LOGITS

 mnie

0.07

ent

0.07

 ağır

0.06

人は

0.06

 많은

0.06

 allied

0.06

Ð

0.06

 governors

0.06

 terrified

0.06

////////////////////////////////////////////////////////////////////////////////////////////////

0.06

Activations Density 0.026%

journal articles

This neuron detects bibliographic citation elements (e.g. reference numbers, years, volumes, page ranges) in the text.

No Comments

No Known Activations