INDEX

Explanations

announcements or safety precautions

np_max-act · gemini-2.0-flash

This neuron detects mentions of COVID-related safety measures and facility status updates (e.g. closures, remote work, precautions, and reopening notices).

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

 판매

-0.07

 Animalia

-0.06

 dedicate

-0.06

賞

-0.06

 legality

-0.06

opher

-0.06

_VO

-0.06

beb

-0.06

yol

-0.06

	elem

-0.06

POSITIVE LOGITS

;-

0.06

Encoded

0.06

 Με

0.06

услов

0.06

až

0.06

сь

0.06

Servlet

0.06

 Martins

0.06

 jealous

0.06

(=

0.06

Activations Density 0.047%

announcements or safety precautions

This neuron detects mentions of COVID-related safety measures and facility status updates (e.g. closures, remote work, precautions, and reopening notices).

No Comments

No Known Activations