INDEX

Explanations

statistical information regarding communities or populations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ocus

-0.15

azzo

-0.14

Ð´ÐµÐ½

-0.14

acket

-0.14

ipp

-0.14

kÃ¼

-0.14

 vidÃ©

-0.14

divide

-0.13

AsStream

-0.13

 Jenner

-0.13

POSITIVE LOGITS

 Cong

0.16

 congen

0.15

 Hack

0.15

 milit

0.15

 active

0.14

 Plantae

0.14

åĲĪãĤıãģĽ

0.14

Cong

0.14

 borrowing

0.13

active

0.13

Activations Density 0.033%

statistical information regarding communities or populations

No Comments

No Known Activations