INDEX

Explanations

technical jargon and expressions related to mathematical modeling

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ëŁ´

-0.15

iffies

-0.14

leigh

-0.14

ë¹Ī

-0.14

#ad

-0.14

ifferential

-0.14

apore

-0.14

kowski

-0.14

avin

-0.13

Ãºi

-0.13

POSITIVE LOGITS

 ground

0.26

 Hubbard

0.22

 frustration

0.20

pla

0.20

 Ground

0.20

 nearest

0.20

 spins

0.20

 magnetic

0.18

 compass

0.18

 magnets

0.18

Activations Density 0.019%

technical jargon and expressions related to mathematical modeling

No Comments

No Known Activations