INDEX

Explanations

answering questions

np_max-act · gemini-2.0-flash

This neuron activates on numeric tokens (digits used for enumeration or numbering).

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

 fatigue

-0.07

 derivatives

-0.07

貸

-0.06

 efficiency

-0.06

ксп

-0.06

 кле

-0.06

eg

-0.06

 mortgage

-0.06

 เก

-0.06

ันยายน

-0.06

POSITIVE LOGITS

 axle

0.07

emas

0.06

_terms

0.06

(json

0.06

(:

0.06

.setAuto

0.06

PK

0.06

bro

0.06

 آهنگ

0.06

Activations Density 0.011%

answering questions

This neuron activates on numeric tokens (digits used for enumeration or numbering).

No Comments

No Known Activations