INDEX

Explanations

references to influential individuals and their contributions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

amma

-0.17

(named

-0.16

ory

-0.15

Ð·Ñĥ

-0.15

 alphabet

-0.15

 unnamed

-0.15

 Alphabet

-0.15

indow

-0.15

ÙĨØ¯ÛĮ

-0.15

 Named

-0.14

POSITIVE LOGITS

mon

0.40

sob

0.36

 handle

0.35

 term

0.31

 alias

0.30

sob

0.30

tag

0.30

handle

0.29

 epith

0.28

 catch

0.28

Activations Density 0.151%

references to influential individuals and their contributions

No Comments

No Known Activations