INDEX

Explanations

life

np_max-act · gemini-2.0-flash

This neuron detects references to art genres or painting subjects, especially terms like “still life,” “landscape,” “portrait,” and similar genre labels.

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

ett

-0.07

	vertices

-0.07

getObject

-0.06

onica

-0.06

asal

-0.06

 testcase

-0.06

Coll

-0.06

.Our

-0.06

cky

-0.06

活

-0.06

POSITIVE LOGITS

 radi

0.06

 Đảng

0.06

'}↵

0.06

 chiff

0.06

醫

0.06

修

0.06

 เพ

0.06

เกษตร

0.06

ença

0.06

플

0.06

Activations Density 0.028%

life

This neuron detects references to art genres or painting subjects, especially terms like “still life,” “landscape,” “portrait,” and similar genre labels.

No Comments

No Known Activations

life

This neuron detects references to art genres or painting subjects, especially terms like “still life,” “landscape,” “portrait,” and similar genre labels.

No Comments

No Known Activations