INDEX

Explanations

references to historical events or notable figures

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

olson

-0.16

Joe

-0.15

GTA

-0.15

ptal

-0.14

Israeli

-0.14

adlo

-0.14

 kola

-0.14

andi

-0.14

 Samoa

-0.14

antan

-0.14

POSITIVE LOGITS

Tud

0.41

 Henry

0.35

 Elizabeth

0.33

 Protestant

0.30

 Catholic

0.29

 Cardinal

0.28

Henry

0.28

 Catholics

0.28

 Anne

0.28

 Wyatt

0.27

Activations Density 0.027%

references to historical events or notable figures

No Comments

No Known Activations