INDEX

Explanations

Code and technical snippets

np_max-act · gemini-2.0-flash

The neuron flags user queries of the form “Is X a Y word?”—i.e. questions asking whether a term belongs to a particular language.

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

oss

-0.07

 стрем

-0.07

Four

-0.07

.ta

-0.07

 스포츠

-0.06

.BLACK

-0.06

わ

-0.06

до

-0.06

 clues

-0.06

 предус

-0.06

POSITIVE LOGITS

 στα

0.07

Detect

0.07

官方

0.06

 Reminder

0.06

"};↵↵

0.06

 prec

0.06

キャ

0.06

FormField

0.06

_Channel

0.06

 fades

0.06

Activations Density 0.286%

Code and technical snippets

The neuron flags user queries of the form “Is X a Y word?”—i.e. questions asking whether a term belongs to a particular language.

No Comments

No Known Activations

Code and technical snippets

The neuron flags user queries of the form “Is X a Y word?”—i.e. questions asking whether a term belongs to a particular language.

No Comments

No Known Activations