INDEX

Explanations

distinctive character representations or symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

 bourbon

-0.15

 Gotham

-0.14

 Cruise

-0.13

 Nordic

-0.13

.contentView

-0.13

 Cleveland

-0.13

 Broadway

-0.13

 Russo

-0.13

isman

-0.12

 Schumer

-0.12

POSITIVE LOGITS

 villagers

0.32

 village

0.31

 Tanzania

0.27

 villages

0.27

HIV

0.27

 Uganda

0.26

 malaria

0.26

NGO

0.26

 Tanz

0.26

 Zambia

0.24

Activations Density 0.145%

distinctive character representations or symbols

No Comments

No Known Activations