INDEX

Explanations

technical terms related to programming and software development

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

afort

-0.14

teb

-0.14

 Verified

-0.14

 dÆ°

-0.13

case

-0.13

 Dank

-0.13

iw

-0.13

NM

-0.13

son

-0.13

 Armstrong

-0.12

POSITIVE LOGITS

okit

0.17

addir

0.16

à¸ı

0.15

arshal

0.15

ÑģÐ»Ð¸

0.15

 {{--<

0.14

zzle

0.14

Ð´Ñĭ

0.14

Ã¡bado

0.14

iferay

0.13

Activations Density 0.101%

technical terms related to programming and software development

No Comments

No Known Activations