INDEX

Explanations

references to biblical stories and characters

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

 Lutheran

-0.15

 ÄĮesk

-0.15

éľĬ

-0.15

Chris

-0.14

 Emirates

-0.14

 Catalan

-0.14

onden

-0.13

 ÄĲÃłi

-0.13

 Alpine

-0.13

 relig

-0.13

POSITIVE LOGITS

 Solomon

0.31

Lot

0.29

Neb

0.29

 Moses

0.29

Job

0.29

 Abraham

0.27

 King

0.26

 Abram

0.25

 Bath

0.25

 Saul

0.25

Activations Density 0.180%

references to biblical stories and characters

No Comments

No Known Activations