INDEX

Explanations

references to natural substances and their properties

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

laws

-0.19

 wines

-0.17

 models

-0.17

posables

-0.16

films

-0.16

 meats

-0.15

 Stocks

-0.15

ë¡Ģ

-0.15

 stocks

-0.15

 languages

-0.15

POSITIVE LOGITS

 substance

0.54

 compound

0.41

 ingredient

0.36

compound

0.36

 Substance

0.36

 molecule

0.34

Compound

0.30

 product

0.30

 Compound

0.29

 drug

0.28

Activations Density 0.328%

references to natural substances and their properties

No Comments

No Known Activations