INDEX

Explanations

solvent

np_max-act · gemini-2.0-flash

The neuron fires on mentions of solvents—especially organic or volatile solvent terms used in coatings and paint formulations.

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

ास

-0.06

โจ

-0.06

asive

-0.06

いう

-0.06

 homemade

-0.06

opsy

-0.06

dashboard

-0.06

ROM

-0.06

ondon

-0.06

ンパ

-0.06

POSITIVE LOGITS

 einf

0.07

 toolStrip

0.06

лих

0.06

 elic

0.06

raphic

0.06

getColumn

0.06

=`

0.06

*>*

0.06

Gas

0.06

Activations Density 0.016%

solvent

The neuron fires on mentions of solvents—especially organic or volatile solvent terms used in coatings and paint formulations.

No Comments

No Known Activations