INDEX

Explanations

terms related to artificial intelligence and automation in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 structure

-0.14

ynamo

-0.14

uliar

-0.14

antino

-0.14

orman

-0.13

åħ¬å¼ı

-0.13

Î¬Î½

-0.13

venes

-0.13

cision

-0.13

phan

-0.13

POSITIVE LOGITS

 technology

0.23

fut

0.22

 technologies

0.21

technology

0.21

 Moore

0.21

 futuro

0.20

 technological

0.20

 technolog

0.20

 Technology

0.18

 Future

0.18

Activations Density 0.249%

terms related to artificial intelligence and automation in various contexts

No Comments

No Known Activations