INDEX

Explanations

post/position

np_max-act · gemini-2.0-flash

This neuron detects words referring to official roles or appointments (e.g., “job,” “position,” “post,” “appointment”).

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

ideographic

-0.06

 undocumented

-0.06

 fruit

-0.06

Folders

-0.06

 Thunder

-0.06

-ev

-0.06

undler

-0.06

ignet

-0.06

_trajectory

-0.06

 spel

-0.06

POSITIVE LOGITS

(IntPtr

0.08

>Edit

0.07

 Weiter

0.07

uelve

0.07

 нер

0.07

菲

0.07

ısıt

0.06

铺

0.06

 ${↵

0.06

:(

0.06

Activations Density 0.018%

post/position

This neuron detects words referring to official roles or appointments (e.g., “job,” “position,” “post,” “appointment”).

No Comments

No Known Activations