INDEX

Explanations

end-of-block or end-of-file indicators in code or text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

znik

-0.15

_CY

-0.15

apan

-0.14

Ash

-0.14

casting

-0.14

bjerg

-0.14

gio

-0.14

å±±å¸Ĥ

-0.13

ÑİÐ½

-0.13

POSITIVE LOGITS

Ð³Ð»ÑıÐ´

0.17

å¸ģ

0.16

erdem

0.16

PPER

0.16

axed

0.15

à¤¾à¤°à¤ķ

0.14

ippets

0.14

reserve

0.14

Gle

0.14

cplusplus

0.14

Activations Density 0.002%

end-of-block or end-of-file indicators in code or text

No Comments

No Known Activations