INDEX

Explanations

code symbols

np_max-act · gemini-2.0-flash

The neuron activates on floating‐point numeric literals (numbers containing a decimal point) in code.

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

submenu

-0.06

Ｃ

-0.06

TOO

-0.06

 BorderLayout

-0.06

ерг

-0.06

Cla

-0.06

("~

-0.06

چار

-0.06

_write

-0.06

 přech

-0.06

POSITIVE LOGITS

 cél

0.07

 specific

0.07

szy

0.06

leg

0.06

wanted

0.06

 generado

0.06

?type

0.06

qi

0.06

ìm

0.06

ucción

0.06

Activations Density 0.046%

code symbols

The neuron activates on floating‐point numeric literals (numbers containing a decimal point) in code.

No Comments

No Known Activations