INDEX

Explanations

A

np_max-act · gemini-2.0-flash

The neuron fires on the special “user” turn‐indicator token, i.e. it flags when a user message header appears.

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

roduction

-0.07

Executing

-0.06

_RETRY

-0.06

edBy

-0.06

 ProgressDialog

-0.06

 conveyed

-0.06

iatrics

-0.06

 Beans

-0.06

-guide

-0.06

 Patron

-0.06

POSITIVE LOGITS

(_

0.07

 QPixmap

0.07

-scrollbar

0.06

fö

0.06

ших

0.06

 Nagar

0.06

 giov

0.06

**(

0.06

vero

0.06

-national

0.06

Activations Density 0.024%

A

The neuron fires on the special “user” turn‐indicator token, i.e. it flags when a user message header appears.

No Comments

No Known Activations