INDEX

Explanations

references to the Harry Potter series and its characters

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

ropolis

-0.16

-0.14

ODB

-0.14

isman

-0.14

.makeText

-0.14

*}

-0.14

 Hamm

-0.14

à¤ľà¤¨

-0.14

POSITIVE LOGITS

 Dumbledore

0.29

 Hogwarts

0.28

 Potter

0.26

 Voldemort

0.25

 Rowling

0.25

 Harry

0.25

Harry

0.24

 Snape

0.22

foy

0.22

Sly

0.21

Activations Density 0.028%

references to the Harry Potter series and its characters

No Comments

No Known Activations