INDEX

Explanations

forge

np_max-act · gemini-2.0-flash

This neuron primarily detects the gerund “forging.”

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

극

-0.07

 кла

-0.07

图

-0.07

incident

-0.07

'L

-0.07

clip

-0.06

ामल

-0.06

LAP

-0.06

quences

-0.06

.lb

-0.06

POSITIVE LOGITS

 forged

0.14

 Forge

0.12

 forge

0.12

forge

0.10

Forge

0.10

 forging

0.09

 forg

0.09

 Forg

0.07

 strive

0.07

 thổ

0.07

Activations Density 0.003%

forge

This neuron primarily detects the gerund “forging.”

No Comments

No Known Activations