INDEX

Explanations

references to sections and practical sessions in a structured document

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

ruba

-0.16

å¤®

-0.15

esseract

-0.14

BOOLE

-0.14

bst

-0.14

getc

-0.14

æħ¶

-0.14

isman

-0.13

/live

-0.13

luÅ¾

-0.13

POSITIVE LOGITS

 Bonus

0.18

 bonus

0.16

Bonus

0.15

 Final

0.15

#:

0.15

Ep

0.14

 Conclusion

0.14

olon

0.14

uze

0.14

 FINAL

0.14

Activations Density 0.011%

references to sections and practical sessions in a structured document

No Comments

No Known Activations