INDEX

Explanations

references to academic journals and publications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

 nackte

-0.15

.chapter

-0.15

alic

-0.14

edm

-0.13

angel

-0.13

ullo

-0.13

 pleasure

-0.13

tro

-0.13

 Passive

-0.13

ç·ł

-0.13

POSITIVE LOGITS

vez

0.17

ovÃŃ

0.16

owie

0.15

 empire

0.15

ÐµÐ½Ð´

0.15

 TokenType

0.14

ismet

0.14

 RedirectTo

0.14

iste

0.14

Ð¾Ð²ÐµÑĢ

0.13

Activations Density 0.028%

references to academic journals and publications

No Comments

No Known Activations