INDEX

Explanations

mathematical equations and expressions

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

iyi

-0.17

er

-0.17

anou

-0.17

ed

-0.16

Ø§

-0.16

-0.14

zburg

-0.14

-0.13

redients

-0.13

POSITIVE LOGITS

uby

0.17

ndef

0.16

ereo

0.14

Éµ

0.14

jos

0.14

xEA

0.13

olan

0.13

/***/

0.13

rous

0.13

comed

0.13

Activations Density 0.174%

mathematical equations and expressions

No Comments

No Known Activations