INDEX

Explanations

references to online resources or external links

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

adem

-0.17

&P

-0.15

owns

-0.15

 Jacqu

-0.15

atik

-0.15

alen

-0.15

leness

-0.15

ancell

-0.15

 Jeans

-0.14

ugal

-0.14

POSITIVE LOGITS

ohl

0.15

ÐµÑĨÑĮ

0.15

 ÙħÙĪØ¨

0.14

ska

0.14

istrovstvÃŃ

0.13

çīĩ

0.13

\CMS

0.13

ovÃŃ

0.13

portun

0.13

iane

0.13

Activations Density 0.386%

references to online resources or external links

No Comments

No Known Activations