INDEX

Explanations

y

np_max-act · gemini-2.0-flash

This neuron is effectively inactive and does not detect any meaningful tokens or patterns.

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

修改

-0.06

 замет

-0.06

люд

-0.06

ManagedObjectContext

-0.06

耀

-0.06

Lan

-0.06

.ColumnHeadersHeightSizeMode

-0.06

が

-0.06

ونية

-0.06

設備

-0.06

POSITIVE LOGITS

(K

0.06

 bool

0.06

my

0.06

 لازم

0.06

 Prop

0.06

 изменения

0.06

 según

0.06

 QtCore

0.06

tparam

0.06

Activations Density 0.016%

y

This neuron is effectively inactive and does not detect any meaningful tokens or patterns.

No Comments

No Known Activations

y

This neuron is effectively inactive and does not detect any meaningful tokens or patterns.

No Comments

No Known Activations