INDEX

Explanations

references to literary works and concepts

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

 Leban

-0.17

ê·

-0.14

.ma

-0.14

SKTOP

-0.14

 Jord

-0.14

 Neptune

-0.14

raud

-0.14

arkan

-0.14

pector

-0.14

 Boise

-0.14

POSITIVE LOGITS

 Winn

0.41

Po

0.37

Mil

0.31

 Christopher

0.30

 Hundred

0.28

Po

0.28

Pig

0.27

 Bear

0.27

 Rabbit

0.26

 Padding

0.25

Activations Density 0.003%

references to literary works and concepts

No Comments

No Known Activations