INDEX

Explanations

phrases related to training and qualifications of professionals

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

iah

-0.15

arrison

-0.14

ulton

-0.14

imei

-0.14

argin

-0.14

itech

-0.14

 Hampshire

-0.14

ownik

-0.14

uet

-0.14

afort

-0.13

POSITIVE LOGITS

åĿ

0.14

licer

0.14

licit

0.14

.googlecode

0.14

enus

0.14

IFA

0.13

ctal

0.13

Deposit

0.13

 GOODMAN

0.13

-trained

0.13

Activations Density 0.038%

phrases related to training and qualifications of professionals

No Comments

No Known Activations