INDEX

Explanations

Code/programming

np_max-act · gemini-2.0-flash

The neuron flags tokens that look like programming‐language syntax (e.g. code punctuation, keywords, braces, semicolons).

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

از

-0.07

至

-0.07

 돌아

-0.06

дн

-0.06

Sampler

-0.06

Raj

-0.06

ढ

-0.06

GIS

-0.06

maf

-0.06

 absorbs

-0.06

POSITIVE LOGITS

ery

0.07

 sexdate

0.06

cls

0.06

ليزية

0.06

유머

0.06

etro

0.06

.friend

0.06

wee

0.06

 المنطقة

0.06

_WORDS

0.06

Activations Density 0.006%

Code/programming

The neuron flags tokens that look like programming‐language syntax (e.g. code punctuation, keywords, braces, semicolons).

No Comments

No Known Activations

Code/programming

The neuron flags tokens that look like programming‐language syntax (e.g. code punctuation, keywords, braces, semicolons).

No Comments

No Known Activations