INDEX

Explanations

references to languages and bilingualism in policy contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

imei

-0.17

ordum

-0.16

ulings

-0.14

ĽĪ

-0.14

antity

-0.14

 FactoryBot

-0.13

olves

-0.13

olen

-0.13

/Dk

-0.13

seo

-0.13

POSITIVE LOGITS

 spoken

0.18

 official

0.16

ä¸Ģç§į

0.16

 oficial

0.16

 Ø±Ø³ÙħÛĮ

0.16

spoken

0.15

 Ð¼Ð¾Ð²Ð¸

0.15

_GU

0.15

 currency

0.15

 Secondary

0.15

Activations Density 0.049%

references to languages and bilingualism in policy contexts

No Comments

No Known Activations