INDEX

Explanations

zero

np_max-act · gemini-2.0-flash

The neuron activates on numeric tokens (digits, numbers) within mathematical expressions.

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

얼

-0.07

اهم

-0.06

 plans

-0.06

Deposit

-0.06

Mbps

-0.06

_payment

-0.06

_future

-0.06

ức

-0.06

_by

-0.06

ским

-0.06

POSITIVE LOGITS

غاز

0.07

 archivo

0.07

.IP

0.06

 боку

0.06

 QIcon

0.06

 github

0.06

 gridSize

0.06

.Chart

0.06

 gangs

0.06

 Vide

0.06

Activations Density 0.003%

zero

The neuron activates on numeric tokens (digits, numbers) within mathematical expressions.

No Comments

No Known Activations

zero

The neuron activates on numeric tokens (digits, numbers) within mathematical expressions.

No Comments

No Known Activations