INDEX

Explanations

terms related to engineering and innovation activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

-0.15

etes

-0.15

inyin

-0.14

erialize

-0.14

 rhythm

-0.14

adil

-0.14

andin

-0.13

Î»ÎµÎ¹

-0.13

anÃ©

-0.13

(=)

-0.13

POSITIVE LOGITS

 Engineering

0.43

 engineering

0.43

 Engineer

0.40

 engineers

0.39

 engineer

0.38

Engineering

0.38

 Engineers

0.36

engineering

0.35

å·¥ç¨ĭ

0.31

 ENGINE

0.29

Activations Density 0.235%

terms related to engineering and innovation activities

No Comments

No Known Activations

terms related to engineering and innovation activities

No Comments

No Known Activations