INDEX

Explanations

references to visual media and images

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

esseract

-0.16

 DÃ¼n

-0.16

ilyn

-0.16

usra

-0.15

åľ¨çº¿éĺħè¯»

-0.15

ÑĸÐ´Ð¾Ð¼

-0.15

ÎºÏģÎ±

-0.15

ildo

-0.15

.writeValue

-0.15

 jspb

-0.15

POSITIVE LOGITS

 stock

0.56

stock

0.51

 Stock

0.50

Stock

0.48

-stock

0.44

 STOCK

0.43

 royalty

0.38

_stock

0.37

.stock

0.37

Roy

0.36

Activations Density 0.061%

references to visual media and images

No Comments

No Known Activations