INDEX

Explanations

congress

np_max-act · gemini-2.0-flash

This neuron never activates on any content—it effectively doesn’t detect or respond to any token.

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

 Writes

-0.08

 OBJECT

-0.06

 impost

-0.06

Лю

-0.06

.Mark

-0.06

Intro

-0.06

_interest

-0.06

 zkou

-0.06

免

-0.06

 nomine

-0.06

POSITIVE LOGITS

 weighing

0.08

[self

0.07

0.06

 weigh

0.06

Context

0.06

rition

0.06

<algorithm

0.06

SAS

0.06

otto

0.06

Activations Density 0.005%

congress

This neuron never activates on any content—it effectively doesn’t detect or respond to any token.

No Comments

No Known Activations