INDEX

Explanations

discussions about innovative concepts and their popularity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

amac

-0.15

 Pound

-0.15

 Culture

-0.14

shaw

-0.14

=sys

-0.13

realm

-0.13

olo

-0.13

Kam

-0.13

acket

-0.13

Ø

-0.13

POSITIVE LOGITS

eut

0.15

quer

0.15

ebo

0.14

WND

0.14

CCR

0.14

gfx

0.13

antity

0.13

utzt

0.13

ibble

0.13

éĺ³åŁİ

0.13

Activations Density 0.045%

discussions about innovative concepts and their popularity

No Comments

No Known Activations