INDEX

Explanations

were

np_max-act · gemini-2.0-flash

This neuron does not respond to any tokens—it never activates.

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

 bgcolor

-0.07

rsp

-0.06

western

-0.06

estatus

-0.06

 조선

-0.06

Pipeline

-0.06

 QStringLiteral

-0.06

PKK

-0.06

โท

-0.06

_ln

-0.06

POSITIVE LOGITS

 Iraqi

0.06

 neighbor

0.06

↵

0.06

得

0.06

 delimited

0.06

 fresh

0.06

(get

0.06

eted

0.06

.case

0.06

bery

0.06

Activations Density 0.000%

were

This neuron does not respond to any tokens—it never activates.

No Comments

No Known Activations