INDEX

Explanations

datab

np_max-act · gemini-2.0-flash

This neuron detects the substring “data” at the start of words—e.g. in “database,” “dataset,” and “databinding.”

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

_bed

-0.07

จะต

-0.07

Bed

-0.06

Brun

-0.06

)="

-0.06

rac

-0.06

Feat

-0.06

pered

-0.06

.variant

-0.06

CU

-0.06

POSITIVE LOGITS

 datab

0.07

_Mode

0.07

 relocate

0.06

scalar

0.06

 erad

0.06

 additives

0.06

creat

0.06

 electronically

0.06

ोब

0.06

園

0.06

Activations Density 0.000%

datab

This neuron detects the substring “data” at the start of words—e.g. in “database,” “dataset,” and “databinding.”

No Comments

No Known Activations