INDEX

Explanations

references to public relations and social issues surrounding iconic figures and events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

vÄĽt

-0.16

licative

-0.16

arde

-0.15

%C

-0.15

ayet

-0.14

ruz

-0.14

Gig

-0.14

idi

-0.14

lettes

-0.14

 Gins

-0.14

POSITIVE LOGITS

ansom

0.15

 veniam

0.14

rede

0.14

dek

0.14

 voks

0.14

/fontawesome

0.14

elden

0.13

ORIGINAL

0.13

à¸Ĳ

0.13

 virtually

0.13

Activations Density 0.088%

references to public relations and social issues surrounding iconic figures and events

No Comments

No Known Activations