INDEX

Explanations

negations and their associated phrases to highlight the complexity of issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

inos

-0.15

Ã¼b

-0.15

esine

-0.14

å®ŀåľ¨

-0.14

ÑģÑĤÐ¸

-0.14

crew

-0.13

 nowhere

-0.13

mp

-0.13

POSITIVE LOGITS

 exclusive

0.28

 limited

0.27

 rocket

0.26

rocket

0.26

 Rocket

0.24

 isolated

0.24

 static

0.22

 just

0.22

 unique

0.22

 reserved

0.22

Activations Density 0.173%

negations and their associated phrases to highlight the complexity of issues

No Comments

No Known Activations