INDEX

Explanations

Conflicts and systems

np_max-act · gemini-2.0-flash

The main thing this neuron does is detect words and phrases that express strong personal motivation or passionate drive.

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

 type

-0.07

filtered

-0.07

�

-0.07

college

-0.06

noticed

-0.06

MX

-0.06

ewed

-0.06

↵		
↵

-0.06

_var

-0.06

POSITIVE LOGITS

Doc

0.07

각

0.06

委

0.06

RUN

0.06

thermal

0.06

 @"↵

0.06

.GetBytes

0.06

 libertin

0.06

 sonuç

0.06

 envelop

0.06

Activations Density 0.222%

Conflicts and systems

The main thing this neuron does is detect words and phrases that express strong personal motivation or passionate drive.

No Comments

No Known Activations

Conflicts and systems

The main thing this neuron does is detect words and phrases that express strong personal motivation or passionate drive.

No Comments

No Known Activations