INDEX

Explanations

Non-English text

np_max-act · gemini-2.0-flash

This neuron detects direct second‐person address pronouns or forms (e.g. “you,” 你, Вам).

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

งศ

-0.07

FirstOrDefault

-0.07

idders

-0.06

 PureComponent

-0.06

	setState

-0.06

Ül

-0.06

statements

-0.06

datasets

-0.06

 fermentation

-0.06

 условия

-0.06

POSITIVE LOGITS

 pada

0.07

/game

0.07

감

0.06

 lửa

0.06

_ray

0.06

*dx

0.06

,status

0.06

เข

0.06

 Handbook

0.06

>You

0.06

Activations Density 0.051%

Non-English text

This neuron detects direct second‐person address pronouns or forms (e.g. “you,” 你, Вам).

No Comments

No Known Activations