INDEX

Explanations

To be (verb forms)

np_max-act · gemini-2.0-flash

The neuron activates on floating‐point numeric values (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

Painter

-0.07

 puff

-0.07

 Afghanistan

-0.06

.Equals

-0.06

 vengeance

-0.06

ıklı

-0.06

етель

-0.06

 sprint

-0.06

ザー

-0.06

imonials

-0.06

POSITIVE LOGITS

HOR

0.06

�

0.06

_rat

0.06

 αυ

0.06

findById

0.06

(){↵

0.06

=nil

0.06

 holy

0.06

_Des

0.06

 پیامبر

0.06

Activations Density 0.058%

To be (verb forms)

The neuron activates on floating‐point numeric values (decimal numbers) in the text.

No Comments

No Known Activations