INDEX

Explanations

add

np_max-act · gemini-2.0-flash

This neuron never fires (all activation values are zero), so it isn’t detecting any particular token 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

 audiences

-0.07

 Sesso

-0.07

_At

-0.06

 pitfalls

-0.06

ể

-0.06

(sin

-0.06

랍

-0.06

ZeroWidthSpace

-0.06

/logs

-0.06

 praises

-0.06

POSITIVE LOGITS

ボ

0.07

 Страна

0.07

ebp

0.07

 Richie

0.07

 progressive

0.07

 pavement

0.06

 infield

0.06

eph

0.06

dist

0.06

 لن

0.06

Activations Density 0.011%

add

This neuron never fires (all activation values are zero), so it isn’t detecting any particular token pattern.

No Comments

No Known Activations