INDEX

Explanations

do

np_max-act · gemini-2.0-flash

This neuron does not consistently activate on any tokens—it remains essentially silent and does not detect a meaningful pattern.

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

 goggles

-0.07

Kam

-0.07

iates

-0.07

lies

-0.07

 індив

-0.07

 pare

-0.06

 Brit

-0.06

 tick

-0.06

 میان

-0.06

 beacon

-0.06

POSITIVE LOGITS

.isEnabled

0.07

 datetime

0.07

 Responsibilities

0.07

ิเศษ

0.07

 ToDo

0.07

眠

0.06

.How

0.06

DidLoad

0.06

conomics

0.06

 ابو

0.06

Activations Density 0.035%

do

This neuron does not consistently activate on any tokens—it remains essentially silent and does not detect a meaningful pattern.

No Comments

No Known Activations

do

This neuron does not consistently activate on any tokens—it remains essentially silent and does not detect a meaningful pattern.

No Comments

No Known Activations