INDEX

Explanations

forum/programming discussions

np_max-act · gemini-2.0-flash

The neuron detects occurrences of the word “repeating,” marking when repetition is being discussed in the text.

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

 extracted

-0.06

Christmas

-0.06

�

-0.06

 Lori

-0.06

 популяр

-0.06

 dataSnapshot

-0.06

.UserId

-0.06

 volts

-0.06

<Scalar

-0.06

umas

-0.06

POSITIVE LOGITS

нее

0.07

VENT

0.06

 mutating

0.06

 seating

0.06

'ya

0.06

 işte

0.06

_T

0.06

 tím

0.06

 completeness

0.06

Activations Density 0.005%

forum/programming discussions

The neuron detects occurrences of the word “repeating,” marking when repetition is being discussed in the text.

No Comments

No Known Activations

forum/programming discussions

The neuron detects occurrences of the word “repeating,” marking when repetition is being discussed in the text.

No Comments

No Known Activations