INDEX

Explanations

digital archives

np_max-act · gemini-2.0-flash

The neuron is triggered by mentions of archival metadata standards and format identifiers (e.g. EAD, METS, ISO numbers, DCC).

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

 univers

-0.06

 Care

-0.06

 care

-0.06

 APPRO

-0.06

ORD

-0.06

_FILTER

-0.06

’den

-0.06

_CAP

-0.06

 admon

-0.06

्तर

-0.06

POSITIVE LOGITS

 موقعیت

0.07

(seed

0.06

이에

0.06

rss

0.06

(rgb

0.06

 empty

0.06

 آسی

0.06

utf

0.06

 getNode

0.06

 peptide

0.06

Activations Density 0.014%

digital archives

The neuron is triggered by mentions of archival metadata standards and format identifiers (e.g. EAD, METS, ISO numbers, DCC).

No Comments

No Known Activations