INDEX

Explanations

discussions about the implications and responsibilities of AI technology

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

éĻµ

-0.17

|/

-0.16

raquo

-0.16

éľĬ

-0.15

electron

-0.15

 methodologies

-0.15

 globalization

-0.14

 Unified

-0.14

amen

-0.14

intel

-0.14

POSITIVE LOGITS

AI

0.29

AI

0.28

 ethical

0.27

 bias

0.27

 algorithm

0.27

Eth

0.25

 ethics

0.25

 Algorithm

0.24

 fairness

0.24

ai

0.23

Activations Density 0.038%

discussions about the implications and responsibilities of AI technology

No Comments

No Known Activations