INDEX

Explanations

black

np_max-act · gemini-2.0-flash

This neuron detects mentions of martial-arts ranks and titles (e.g. belt degrees, master/grandmaster designations).

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Gaussian

-0.07

Yer

-0.07

 oldest

-0.06

 anecd

-0.06

_https

-0.06

_LANGUAGE

-0.06

_LED

-0.06

 Dans

-0.06

_rotation

-0.06

 Simulation

-0.06

POSITIVE LOGITS

upported

0.08

	initialize

0.07

 patch

0.07

ặ

0.07

etail

0.06

 같습니다

0.06

 तल

0.06

-Americ

0.06

 bilder

0.06

 Curtis

0.06

Activations Density 0.005%

black

This neuron detects mentions of martial-arts ranks and titles (e.g. belt degrees, master/grandmaster designations).

No Comments

No Known Activations