INDEX

Explanations

a

np_max-act · gemini-2.0-flash

The neuron never activates on any input—it doesn’t detect or respond to any textual 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

_dup

-0.07

ُع

-0.06

 statutory

-0.06

COMMON

-0.06

.ObjectModel

-0.06

 stuffing

-0.06

 shar

-0.06

 thoát

-0.06

 شن

-0.06

 funct

-0.06

POSITIVE LOGITS

 قبل

0.07

�

0.07

 अलग

0.06

шин

0.06

 हट

0.06

;amp

0.06

 Biom

0.06

uers

0.06

Nur

0.06

Activations Density 0.043%

a

The neuron never activates on any input—it doesn’t detect or respond to any textual pattern.

No Comments

No Known Activations

a

The neuron never activates on any input—it doesn’t detect or respond to any textual pattern.

No Comments

No Known Activations