INDEX

Explanations

automation

np_max-act · gemini-2.0-flash

The neuron flags mentions of “autom*” terms—words like automation, automate, automating, workflows, and related task-automation vocabulary.

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

currently

-0.07

whether

-0.07

 pancre

-0.07

Digest

-0.07

 Operating

-0.07

 isot

-0.06

никами

-0.06

zero

-0.06

얼

-0.06

ندان

-0.06

POSITIVE LOGITS

้าว

0.07

 még

0.06

_ROOM

0.06

 Ні

0.06

 Lucia

0.06

/year

0.06

 المنطقة

0.06

Ste

0.06

walking

0.06

.IsSuccess

0.06

Activations Density 0.020%

automation

The neuron flags mentions of “autom*” terms—words like automation, automate, automating, workflows, and related task-automation vocabulary.

No Comments

No Known Activations