INDEX

Explanations

content related to quizzes and trivia

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ÙĨØ¯ÙĬ

-0.15

rvine

-0.15

 ì¶ľìŀ¥

-0.15

è¸ı

-0.13

 Komment

-0.13

 yorum

-0.13

åĿª

-0.13

 Kushner

-0.13

æī¹

-0.13

 subTitle

-0.12

POSITIVE LOGITS

 quiz

0.39

 facts

0.39

quiz

0.36

 trivia

0.35

 fact

0.34

 Facts

0.34

 quizzes

0.34

facts

0.33

 Fact

0.32

 Quiz

0.32

Activations Density 0.179%

content related to quizzes and trivia

No Comments

No Known Activations