INDEX

Explanations

elements related to theater productions and credits

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

-0.15

rdf

-0.15

ë§Ŀ

-0.15

 Maher

-0.15

 Mono

-0.14

oration

-0.14

ÐºÑĥÐ»

-0.14

ìĿ´ëĵľ

-0.14

Ã¨m

-0.14

izen

-0.13

POSITIVE LOGITS

 Broadway

0.32

Broad

0.30

 broad

0.22

 Rodgers

0.20

cab

0.19

 Musical

0.19

cab

0.18

 cast

0.18

 Equity

0.18

 productions

0.18

Activations Density 0.099%

elements related to theater productions and credits

No Comments

No Known Activations