INDEX

Explanations

references to specific authors or notable figures in various fields

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

Ð»ÐºÐ¸

-0.16

à¸ĩà¸²à¸Ļ

-0.15

egers

-0.14

zbo

-0.14

Ã¡tek

-0.14

 soaking

-0.14

ä¸ĬãģĴ

-0.14

zend

-0.14

.LoggerFactory

-0.14

avior

-0.14

POSITIVE LOGITS

ility

0.20

itional

0.18

ambique

0.18

oplay

0.17

ëŀĺ

0.17

oved

0.17

ost

0.16

eller

0.16

ilda

0.15

0.14

Activations Density 0.066%

references to specific authors or notable figures in various fields

No Comments

No Known Activations