INDEX

Explanations

smart

np_max-act · gemini-2.0-flash

The neuron activates whenever the token “smart” appears (e.g. in “smart home,” “smart grid,” “smart devices,” etc.).

oai_token-act-pair · o4-mini Triggered by @xinyanhu8

devices and applications related to smart technology and automation in home and healthcare settings.

oai_token-act-pair · gpt-4o-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

omidou

-0.07

<Type

-0.07

 Martinez

-0.07

 Holmes

-0.06

 Horton

-0.06

_skb

-0.06

 mansion

-0.06

zoo

-0.06

 allo

-0.06

wort

-0.06

POSITIVE LOGITS

 Intelligent

0.08

 smart

0.07

 intelligent

0.07

elligent

0.07

Concept

0.06

 Context

0.06

IMPLIED

0.06

 getContext

0.06

FormattedMessage

0.06

ListView

0.06

Activations Density 0.009%

smart

The neuron activates whenever the token “smart” appears (e.g. in “smart home,” “smart grid,” “smart devices,” etc.).

devices and applications related to smart technology and automation in home and healthcare settings.

No Comments

No Known Activations