INDEX

Explanations

concepts and terminology associated with algorithms and evolutionary biology

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

 Pulse

-0.16

baugh

-0.15

 saturn

-0.14

ocide

-0.14

uxtap

-0.14

ollower

-0.14

 Accent

-0.14

ç«ľ

-0.14

LEV

-0.14

isle

-0.13

POSITIVE LOGITS

 posterior

0.39

Bay

0.35

 poster

0.30

Bay

0.30

pri

0.30

 likelihood

0.29

 prior

0.28

 marginal

0.27

.poster

0.26

bay

0.26

Activations Density 0.008%

concepts and terminology associated with algorithms and evolutionary biology

No Comments

No Known Activations