INDEX

Explanations

Temples and shrines

np_max-act · gemini-2.0-flash

This neuron detects references to Hindu temples or their associated deities (e.g. words like “Temple,” “deity,” “idol,” and specific shrine names).

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

 users

-0.07

 download

-0.07

ons

-0.06

Norm

-0.06

 analyzer

-0.06

parms

-0.06

_EN

-0.06

مح

-0.06

PCODE

-0.06

 stripped

-0.06

POSITIVE LOGITS

 πιο

0.07

�

0.07

 siempre

0.07

 flawed

0.07

 siyasi

0.07

 시즌

0.06

keiten

0.06

чук

0.06

?,?,?,?,

0.06

 लगभग

0.06

Activations Density 0.021%

Temples and shrines

This neuron detects references to Hindu temples or their associated deities (e.g. words like “Temple,” “deity,” “idol,” and specific shrine names).

No Comments

No Known Activations

Temples and shrines

This neuron detects references to Hindu temples or their associated deities (e.g. words like “Temple,” “deity,” “idol,” and specific shrine names).

No Comments

No Known Activations