INDEX

Explanations

numeric data or values associated with historical timelines and events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

isen

-0.14

greg

-0.13

uÄį

-0.13

vox

-0.13

Ø±ÛĮØ²

-0.12

ì§ĵ

-0.12

agua

-0.12

ensen

-0.12

imizer

-0.12

auer

-0.12

POSITIVE LOGITS

th

0.42

teenth

0.31

 century

0.30

eenth

0.29

venth

0.28

 centuries

0.28

th

0.28

-century

0.28

 Century

0.27

enth

0.26

Activations Density 0.016%

numeric data or values associated with historical timelines and events

No Comments

No Known Activations