INDEX

Explanations

phrases indicating statistical or numerical information related to events or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

à¤²à¤¬

-0.16

ibrator

-0.15

iddi

-0.14

å²¸

-0.14

 Aviv

-0.14

alem

-0.14

 Rune

-0.14

 Singap

-0.14

ael

-0.14

IDES

-0.14

POSITIVE LOGITS

 Fresno

0.39

Tul

0.31

Clo

0.29

 Fres

0.27

 fres

0.27

Vis

0.27

 Kern

0.26

0.25

 Yosemite

0.24

 Kings

0.23

Activations Density 0.010%

phrases indicating statistical or numerical information related to events or entities

No Comments

No Known Activations