INDEX

Explanations

lio

np_max-act · gemini-2.0-flash

This neuron activates on the “biblio”-related tokens marking bibliography or citation sections.

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

 dimin

-0.07

TouchListener

-0.06

localctx

-0.06

Di

-0.06

Client

-0.06

)=>{↵

-0.06

Introduced

-0.06

>>>>>>>

-0.06

Nut

-0.06

packet

-0.06

POSITIVE LOGITS

ительного

0.08

άβ

0.07

 оборуд

0.07

 espec

0.07

 irgend

0.06

ोम

0.06

もし

0.06

 more

0.06

erez

0.06

js

0.06

Activations Density 0.001%

lio

This neuron activates on the “biblio”-related tokens marking bibliography or citation sections.

No Comments

No Known Activations

lio

This neuron activates on the “biblio”-related tokens marking bibliography or citation sections.

No Comments

No Known Activations