INDEX

Explanations

appearance, clothing

np_max-act · gemini-2.0-flash

The neuron responds to descriptive modifiers—adjectives and adverbs—that intensify sensory or visual detail, especially in erotic or appearance-focused 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

NGC

-0.07

mug

-0.06

ouchers

-0.06

 Jeffrey

-0.06

 Priv

-0.06

Ah

-0.06

shape

-0.06

 zakáz

-0.06

 addObject

-0.06

/target

-0.06

POSITIVE LOGITS

π

0.07

语言

0.06

zept

0.06

AVG

0.06

 series

0.06

erre

0.06

QUENCY

0.06

 Πέ

0.06

arım

0.06

raits

0.06

Activations Density 0.023%

appearance, clothing

The neuron responds to descriptive modifiers—adjectives and adverbs—that intensify sensory or visual detail, especially in erotic or appearance-focused contexts.

No Comments

No Known Activations