INDEX

Explanations

go

np_max-act · gemini-2.0-flash

This neuron fires on numeric literals (e.g. integers or floating-point numbers) throughout 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ｭ

-0.08

Ket

-0.07

Nobody

-0.06

dem

-0.06

ीट

-0.06

 پرد

-0.06

Plans

-0.06

 pregnant

-0.06

_REG

-0.06

 гаран

-0.06

POSITIVE LOGITS

 POSSIBILITY

0.07

COM

0.07

.Authentication

0.07

>');↵

0.06

іли

0.06

.only

0.06

 serializer

0.06

thren

0.06

>Delete

0.06

 Bundle

0.06

Activations Density 0.065%

go

This neuron fires on numeric literals (e.g. integers or floating-point numbers) throughout the text.

No Comments

No Known Activations