INDEX

Explanations

Code/Programming

np_max-act · gemini-2.0-flash

This neuron activates on numeric tokens representing decimal fractions (numbers with a decimal point and following digits).

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

 workload

-0.08

imest

-0.07

.COMP

-0.07

ayd

-0.07

	vertex

-0.07

 Cunning

-0.07

 flats

-0.07

 pelo

-0.06

머

-0.06

 dět

-0.06

POSITIVE LOGITS

싸

0.07

wake

0.06

чук

0.06

 supper

0.05

_lim

0.05

 هزینه

0.05

Ung

0.05

 AUDIO

0.05

ecera

0.05

Activations Density 0.508%

Code/Programming

This neuron activates on numeric tokens representing decimal fractions (numbers with a decimal point and following digits).

No Comments

No Known Activations

Code/Programming

This neuron activates on numeric tokens representing decimal fractions (numbers with a decimal point and following digits).

No Comments

No Known Activations