INDEX

Explanations

news articles

np_max-act · gemini-2.0-flash

The neuron lights up on key content words—especially descriptive verbs and nouns—rather than on common function words.

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

년에는

-0.07

 Savage

-0.07

ResultsController

-0.07

 dữ

-0.06

uat

-0.06

 cellFor

-0.06

{*

-0.06

受到

-0.06

POSITIVE LOGITS

 collaborations

0.06

 Highlights

0.06

 Determines

0.06

 complaining

0.06

central

0.06

.Employee

0.06

 national

0.06

 trends

0.06

angled

0.06

 TRANS

0.06

Activations Density 0.215%

news articles

The neuron lights up on key content words—especially descriptive verbs and nouns—rather than on common function words.

No Comments

No Known Activations