INDEX

Explanations

warm

np_max-act · gemini-2.0-flash

The neuron activates on descriptive terms highlighting the softness, warmth, and luxurious texture of fibers (e.g., “warmth,” “soft,” “durable,” “luxurious,” “texture”).

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

 امکان

-0.07

 pigeon

-0.07

 thụ

-0.06

mis

-0.06

 интер

-0.06

 سایر

-0.06

 CONTRIBUT

-0.06

edReader

-0.06

.keySet

-0.06

�

-0.06

POSITIVE LOGITS

átu

0.07

 Tarif

0.06

 Wales

0.06

атель

0.06

 комплекс

0.06

اة

0.06

 Classifier

0.06

Colors

0.06

_STRUCT

0.06

 shootout

0.06

Activations Density 0.003%

warm

The neuron activates on descriptive terms highlighting the softness, warmth, and luxurious texture of fibers (e.g., “warmth,” “soft,” “durable,” “luxurious,” “texture”).

No Comments

No Known Activations