INDEX

Explanations

thread

np_max-act · gemini-2.0-flash

This neuron activates on mentions of threads (e.g. “thread,” “threads,” “main thread”) in code or explanations.

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

 Cast

-0.07

なんだ

-0.07

 [];↵↵

-0.07

 رمضان

-0.06

 referencing

-0.06

 привед

-0.06

KA

-0.06

アルバ

-0.06

Sleep

-0.06

yre

-0.06

POSITIVE LOGITS

.Experimental

0.07

 electrons

0.07

+l

0.07

τικο

0.06

*\

0.06

 Liebe

0.06

-loving

0.06

 mutual

0.06

_Action

0.06

HideInInspector

0.06

Activations Density 0.008%

thread

This neuron activates on mentions of threads (e.g. “thread,” “threads,” “main thread”) in code or explanations.

No Comments

No Known Activations