INDEX

Explanations

mentions of the term "Vicar."

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

abic

-0.17

rollo

-0.16

IZED

-0.16

Nev

-0.15

ized

-0.15

alsy

-0.15

 Affordable

-0.15

icamente

-0.14

IFA

-0.14

eing

-0.14

POSITIVE LOGITS

arious

0.31

ente

0.30

inity

0.23

enza

0.23

ENTE

0.22

tor

0.21

ARIO

0.21

entes

0.20

ariate

0.19

ory

0.19

Activations Density 0.006%

mentions of the term "Vicar."

No Comments

No Known Activations