INDEX

Explanations

references to programming conventions and terms related to casing of identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

 comma

-0.15

¼åĲĪ

-0.15

rim

-0.14

 Mass

-0.14

etro

-0.14

ury

-0.14

esion

-0.14

ullan

-0.14

ruh

-0.14

isco

-0.13

POSITIVE LOGITS

 capital

0.40

capital

0.35

 Capital

0.35

 capitals

0.34

 CAPITAL

0.32

Capital

0.32

 caps

0.31

 upper

0.31

 lower

0.30

 Capitals

0.29

Activations Density 0.154%

references to programming conventions and terms related to casing of identifiers

No Comments

No Known Activations