INDEX

Explanations

cycle

np_max-act · gemini-2.0-flash

This neuron detects mentions of motorcycles (and related forms of the word).

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

 Lease

-0.07

引用

-0.07

 он

-0.07

 Debbie

-0.06

 Plans

-0.06

(builder

-0.06

 베스트

-0.06

(of

-0.06

 Families

-0.06

 Gros

-0.06

POSITIVE LOGITS

 motorcycle

0.07

 DataGridView

0.07

 strconv

0.07

 motorcycles

0.07

_PRIORITY

0.06

uther

0.06

esty

0.06

 Moto

0.06

 Motorcycle

0.06

.toDouble

0.06

Activations Density 0.003%

cycle

This neuron detects mentions of motorcycles (and related forms of the word).

No Comments

No Known Activations