INDEX

Explanations

mathematical equations and notations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

eson

-0.17

clerosis

-0.15

atsu

-0.14

fir

-0.14

utf

-0.14

oog

-0.13

ido

-0.13

rams

-0.13

ordes

-0.13

æ³£

-0.13

POSITIVE LOGITS

ìĺ¥

0.14

Ð»Ð¸ÑĪ

0.14

-Ta

0.14

.classes

0.14

yii

0.14

zes

0.13

Ta

0.13

itizen

0.13

íı´

0.13

Activations Density 0.038%

mathematical equations and notations

No Comments

No Known Activations