INDEX

Explanations

references to notable authors and literary figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

-0.15

eldorf

-0.14

íĽĦ

-0.14

onz

-0.14

 Carly

-0.14

iglia

-0.14

HL

-0.14

æĶ¹éĿ©

-0.13

ktion

-0.13

POSITIVE LOGITS

 Fantastic

0.24

 Chamber

0.23

Fantastic

0.22

umbledore

0.19

Sor

0.18

 Rowling

0.18

 chamber

0.18

hog

0.18

DH

0.18

Klo

0.18

Activations Density 0.008%

references to notable authors and literary figures

No Comments

No Known Activations