INDEX

Explanations

Published

np_max-act · gemini-2.0-flash

This neuron detects publication metadata, specifically timestamps (dates, times, and the word “Published”).

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

shares

-0.07

центра

-0.07

 από

-0.07

enance

-0.07

oppable

-0.06

âb

-0.06

amping

-0.06

veyor

-0.06

.getOutputStream

-0.06

 eyes

-0.06

POSITIVE LOGITS

Published

0.08

 여러

0.07

SEO

0.07

Timing

0.07

istani

0.07

 düz

0.06

 Кри

0.06

Clazz

0.06

 sayıda

0.06

 citiz

0.06

Activations Density 0.003%

Published

This neuron detects publication metadata, specifically timestamps (dates, times, and the word “Published”).

No Comments

No Known Activations