INDEX

Explanations

configuration files/ports

np_max-act · gemini-2.0-flash

This neuron responds to numeric tokens—especially decimal numbers—within 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

-feature

-0.07

 thousands

-0.07

-control

-0.06

 Mour

-0.06

 müdür

-0.06

longitude

-0.06

SW

-0.06

ениями

-0.06

(_)

-0.06

POSITIVE LOGITS

 parl

0.06

个

0.06

in

0.06

ヴィ

0.06

abay

0.06

 Прав

0.06

 intermittent

0.06

 Interested

0.06

 drib

0.06

 düş

0.06

Activations Density 0.004%

configuration files/ports

This neuron responds to numeric tokens—especially decimal numbers—within the text.

No Comments

No Known Activations