INDEX

Explanations

present

np_max-act · gemini-2.0-flash

This neuron detects promotional announcement phrases in marketing copy (e.g. “proud to present,” “is proud to present,” “we proudly present”).

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

 cultivated

-0.07

 구글

-0.07

Ord

-0.07

DisplayStyle

-0.06

 prim

-0.06

.valor

-0.06

Eric

-0.06

 grpc

-0.06

เคย

-0.06

 Fucked

-0.06

POSITIVE LOGITS

"<?

0.07

 profoundly

0.06

 Replies

0.06

лу

0.06

 payload

0.06

 асп

0.06

 συμπ

0.06

 onNext

0.06

 somebody

0.06

.cz

0.06

Activations Density 0.021%

present

This neuron detects promotional announcement phrases in marketing copy (e.g. “proud to present,” “is proud to present,” “we proudly present”).

No Comments

No Known Activations