INDEX

Explanations

Code examples/snippets

np_max-act · gemini-2.0-flash

This neuron specializes in detecting the literal marker “Text” (and its following punctuation) that introduces the content section.

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

 played

-0.08

 affected

-0.07

itta

-0.07

ANN

-0.06

 returning

-0.06

.Cancel

-0.06

 octave

-0.06

.bottom

-0.06

 attorney

-0.06

Seed

-0.06

POSITIVE LOGITS

�

0.07

 misogyn

0.06

twig

0.06

 binh

0.06

ening

0.06

_GRE

0.06

�

0.06

 neler

0.06

addPreferredGap

0.06

inheritDoc

0.06

Activations Density 0.028%

Code examples/snippets

This neuron specializes in detecting the literal marker “Text” (and its following punctuation) that introduces the content section.

No Comments

No Known Activations