INDEX

Explanations

terms related to automation and its impact on jobs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

Umb

-0.15

ãĥªãĤ«

-0.15

.unlock

-0.14

foy

-0.14

actics

-0.14

à¹ģà¸ģ

-0.14

 accessory

-0.14

RACT

-0.14

ioms

-0.14

_unlock

-0.14

POSITIVE LOGITS

 automation

0.32

 robot

0.32

 robots

0.31

 Automation

0.31

.robot

0.30

 autom

0.29

 Autom

0.28

 machines

0.27

robot

0.27

 bots

0.27

Activations Density 0.193%

terms related to automation and its impact on jobs

No Comments

No Known Activations