INDEX

Explanations

punctuation marks, particularly question marks and periods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

-0.17

'.$

-0.16

ÂĿ

-0.16

 corners

-0.15

 boil

-0.15

tal

-0.15

ssize

-0.14

ľ

-0.14

POSITIVE LOGITS

iddi

0.18

”↵

0.17

Ã¦r

0.16

 ”↵

0.16

ulton

0.16

uyá»ĥn

0.15

elles

0.15

åĪ·

0.15

Ã¼ven

0.15

á»Ľ

0.15

Activations Density 0.026%

punctuation marks, particularly question marks and periods

No Comments

No Known Activations