INDEX

Explanations

references to stock photos and their credits

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

 Redistributions

-0.17

esseract

-0.16

amework

-0.15

untime

-0.15

usra

-0.15

ÑĸÐ´Ð¾Ð¼

-0.15

brane

-0.15

IMIT

-0.15

UrlParser

-0.15

hangi

-0.14

POSITIVE LOGITS

 stock

0.59

stock

0.56

 Stock

0.54

Stock

0.51

-stock

0.47

 STOCK

0.45

_stock

0.40

 stocks

0.39

.stock

0.39

(stock

0.39

Activations Density 0.040%

references to stock photos and their credits

No Comments

No Known Activations