INDEX

Explanations

long

np_max-act · gemini-2.0-flash

This neuron activates on mentions of hair length or style, especially “long” hair descriptions.

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

ANTA

-0.07

 parade

-0.07

 rico

-0.06

 SESSION

-0.06

_buf

-0.06

 buff

-0.06

pop

-0.06

 priest

-0.06

beans

-0.06

_DEL

-0.06

POSITIVE LOGITS

.getTime

0.07

licant

0.07

 Milano

0.06

 مستق

0.06

 рекоменда

0.06

线

0.06

 Arrange

0.06

 consultancy

0.06

 заключ

0.06

 період

0.06

Activations Density 0.009%

long

This neuron activates on mentions of hair length or style, especially “long” hair descriptions.

No Comments

No Known Activations