INDEX

Explanations

non-Latin characters or possibly encoded text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

"<?

-0.16

Åº

-0.15

dn

-0.14

ç´Ģ

-0.14

 Cush

-0.14

.Toolkit

-0.14

Į¨

-0.14

 Ð¾Ð±Ñĭ

-0.14

 explos

-0.14

robe

-0.14

POSITIVE LOGITS

 Bulgarian

0.30

 Bulgaria

0.29

 Sofia

0.27

elerik

0.22

 Telerik

0.22

 Bulg

0.22

 Dimit

0.19

 Burg

0.18

 Ø¨ÙĦØº

0.17

 Macedonia

0.17

Activations Density 0.093%

non-Latin characters or possibly encoded text

No Comments

No Known Activations