INDEX

Explanations

mentions of "Notre Dame."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

ses

-0.16

uet

-0.15

agoon

-0.15

alach

-0.14

.cloudflare

-0.14

SessionFactory

-0.14

åĲ¦

-0.14

 gravity

-0.14

goo

-0.13

ees

-0.13

POSITIVE LOGITS

 Dame

0.40

ame

0.28

 dame

0.26

AME

0.22

dam

0.22

amer

0.21

Dam

0.19

 dames

0.19

Dam

0.19

ames

0.18

Activations Density 0.003%

mentions of "Notre Dame."

No Comments

No Known Activations