INDEX

Explanations

leading

np_max-act · gemini-2.0-flash

The neuron flags mentions of a player or team “leading” in a statistical category (e.g. “leading scorer,” “leading rusher,” etc.).

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

 Countdown

-0.07

Timeout

-0.07

warehouse

-0.06

-shadow

-0.06

 Congressional

-0.06

 Masks

-0.06

향

-0.06

 answers

-0.06

 reviewing

-0.06

Vul

-0.06

POSITIVE LOGITS

(ep

0.07

*>(

0.06

AJ

0.06

REMOTE

0.06

 دفتر

0.06

řízení

0.06

 đỏ

0.06

岛

0.06

 gerek

0.06

ايات

0.06

Activations Density 0.015%

leading

The neuron flags mentions of a player or team “leading” in a statistical category (e.g. “leading scorer,” “leading rusher,” etc.).

No Comments

No Known Activations

leading

The neuron flags mentions of a player or team “leading” in a statistical category (e.g. “leading scorer,” “leading rusher,” etc.).

No Comments

No Known Activations