INDEX

Explanations

references to significant achievements or milestones

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

kul

-0.15

àµį

-0.15

Ø¨Ø§ØŃ

-0.14

 miÃªu

-0.14

 tier

-0.14

±ä¹Ĳ

-0.14

kv

-0.14

Ã²i

-0.14

Sew

-0.14

angan

-0.14

POSITIVE LOGITS

boards

0.17

TouchUpInside

0.14

erable

0.14

allery

0.14

ivet

0.14

omid

0.14

ĨĴ

0.14

è¿

0.14

ãģ¨ãģĨ

0.13

/problem

0.13

Activations Density 0.003%

references to significant achievements or milestones

No Comments

No Known Activations