INDEX

Explanations

information about Amazon's business practices and employee experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

aos

-0.15

anagan

-0.15

emap

-0.14

oise

-0.14

ady

-0.14

 Sext

-0.14

usra

-0.14

 Yorkshire

-0.13

asto

-0.13

POSITIVE LOGITS

 Amazon

0.41

Amazon

0.37

 amazon

0.33

.amazon

0.31

AWS

0.29

amazon

0.29

 Seattle

0.28

.AWS

0.26

/aws

0.26

 Kindle

0.25

Activations Density 0.034%

information about Amazon's business practices and employee experiences

No Comments

No Known Activations