INDEX

Explanations

Encryption and privacy

np_max-act · gemini-2.0-flash

recommendations for securing sensitive information in systems.

oai_token-act-pair · gpt-4o-mini Triggered by @xinyanhu8

The neuron predominantly activates on short, common function words (e.g. pronouns, determiners, conjunctions).

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

Fabric

-0.07

 Cabinets

-0.07

_sub

-0.07

watch

-0.07

AI

-0.06

 toujours

-0.06

ernational

-0.06

fake

-0.06

 Cecil

-0.06

 Governments

-0.06

POSITIVE LOGITS

予約

0.07

úp

0.07

 Scarlet

0.07

自分

0.06

(productId

0.06

 ออนไลน

0.06

ates

0.06

pkg

0.06

.Toggle

0.06

(min

0.06

Activations Density 0.017%

Encryption and privacy

recommendations for securing sensitive information in systems.

The neuron predominantly activates on short, common function words (e.g. pronouns, determiners, conjunctions).

No Comments

No Known Activations