INDEX

Explanations

Agreement/Acknowledgement

np_max-act · gemini-2.0-flash

The neuron detects brief conversational acknowledgments or confirmations (e.g. “ok,” “sure,” “got it”).

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

JSON

-0.07

incl

-0.06

pull

-0.06

indic

-0.06

ideos

-0.06

 Instruments

-0.06

(Tag

-0.06

purpose

-0.06

 celebrates

-0.05

parameters

-0.05

POSITIVE LOGITS

ğinin

0.07

pike

0.07

ИТ

0.07

able

0.06

 कन

0.06

 Occupational

0.06

 palp

0.06

抓

0.06

ORMAT

0.06

[v

0.06

Activations Density 0.048%

Agreement/Acknowledgement

The neuron detects brief conversational acknowledgments or confirmations (e.g. “ok,” “sure,” “got it”).

No Comments

No Known Activations