INDEX

Explanations

data

np_max-act · gemini-2.0-flash

This neuron responds to mentions of data and analytics (e.g., “data,” “analytics,” “predictive,” “driven”) in the text.

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

\modules

-0.06

 guarded

-0.06

 справи

-0.06

 incorporating

-0.06

reements

-0.06

 SCHOOL

-0.06

heten

-0.06

 بیشتری

-0.06

 coroutine

-0.06

>v

-0.06

POSITIVE LOGITS

 الدم

0.07

MSI

0.07

CIS

0.07

++)↵

0.06

pp

0.06

ffmpeg

0.06

 divorce

0.06

ağ

0.06

 portal

0.06

leo

0.06

Activations Density 0.033%

data

This neuron responds to mentions of data and analytics (e.g., “data,” “analytics,” “predictive,” “driven”) in the text.

No Comments

No Known Activations