INDEX

Explanations

number 2

np_max-act · gemini-2.0-flash

The neuron activates on numeric literal tokens (integer or decimal numbers) 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

Ten

-0.08

 undergone

-0.06

having

-0.06

zerbai

-0.06

large

-0.06

 fifteen

-0.06

Из

-0.06

_DH

-0.06

/modal

-0.06

 теч

-0.06

POSITIVE LOGITS

 сигн

0.07

icks

0.07

 frem

0.07

)b

0.07

 сол

0.06

	Buffer

0.06

.writeFileSync

0.06

:ｉ

0.06

�

0.06

 endiş

0.06

Activations Density 0.021%

number 2

The neuron activates on numeric literal tokens (integer or decimal numbers) in the text.

No Comments

No Known Activations

number 2

The neuron activates on numeric literal tokens (integer or decimal numbers) in the text.

No Comments

No Known Activations