INDEX

Explanations

Punctuation

np_max-act · gemini-2.0-flash

This neuron is essentially inactive (a “dead” neuron) and does not consistently respond to any particular text feature.

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

_unlock

-0.07

 Brigham

-0.06

ोप

-0.06

局

-0.06

 Patton

-0.06

 setters

-0.06

gie

-0.06

 duke

-0.06

 vyvol

-0.06

LOD

-0.06

POSITIVE LOGITS

 pixel

0.07

---@

0.06

_Style

0.06

.constants

0.06

removeClass

0.06

_Description

0.06

()?>

0.06

 جستارهای

0.06

ชาย

0.06

)(↵

0.06

Activations Density 0.004%

Punctuation

This neuron is essentially inactive (a “dead” neuron) and does not consistently respond to any particular text feature.

No Comments

No Known Activations