INDEX

Explanations

phrases pertaining to the original publication and context of articles or posts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

oki

-0.16

aru

-0.15

odox

-0.15

 personality

-0.14

ìħľ

-0.14

anlÄ±

-0.14

 immobil

-0.14

cha

-0.14

VS

-0.13

POSITIVE LOGITS

zung

0.17

.scalablytyped

0.16

.xls

0.16

/live

0.15

':''

0.14

else

0.14

cko

0.14

ÐµÐºÐ¾

0.14

åĿĤ

0.14

 serialized

0.14

Activations Density 0.024%

phrases pertaining to the original publication and context of articles or posts

No Comments

No Known Activations