INDEX

Explanations

references to specific operas and their elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

kov

-0.16

misc

-0.15

abar

-0.15

istÃ©

-0.15

 morale

-0.14

UTO

-0.14

MSN

-0.14

 pint

-0.14

Î»Î·

-0.14

ya

-0.14

POSITIVE LOGITS

ADING

0.15

orden

0.14

iller

0.14

fony

0.14

gum

0.13

grounds

0.13

 repl

0.13

GO

0.13

deal

0.13

indy

0.13

Activations Density 0.003%

references to specific operas and their elements

No Comments

No Known Activations