INDEX

Explanations

references to the "Star Wars" franchise, particularly the theme of good versus evil in its narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

 Broncos

-0.17

imen

-0.17

aval

-0.16

 crown

-0.16

imet

-0.15

 Denver

-0.15

 Dion

-0.15

 Oregon

-0.15

syscall

-0.15

_va

-0.15

POSITIVE LOGITS

 Skywalker

0.20

 Jedi

0.19

 Galactic

0.17

Abu

0.17

ÐµÑģÐ¿

0.16

 Star

0.16

 Leia

0.15

Atlanta

0.15

 Peach

0.15

 Galaxy

0.15

Activations Density 0.088%

references to the "Star Wars" franchise, particularly the theme of good versus evil in its narratives

No Comments

No Known Activations