INDEX

Explanations

references to historical events and their implications

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

 Bollywood

-0.18

iou

-0.15

Miami

-0.15

 Ranch

-0.15

alet

-0.15

ombo

-0.14

orca

-0.14

ÙĪØ§Ø¡

-0.14

 Miami

-0.14

 NASA

-0.14

POSITIVE LOGITS

 Kaiser

0.34

Pr

0.32

 Aust

0.31

 Vers

0.29

 Germany

0.27

 Austria

0.26

 Triple

0.26

 Wilhelm

0.25

Ent

0.25

 German

0.25

Activations Density 0.039%

references to historical events and their implications

No Comments

No Known Activations