INDEX

Explanations

key information related to medical professionals and their qualifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

ollah

-0.17

uran

-0.16

omb

-0.15

ANTE

-0.14

xFB

-0.14

ritte

-0.14

ANE

-0.14

odel

-0.14

forman

-0.13

locker

-0.13

POSITIVE LOGITS

 studied

0.36

 earned

0.34

 degrees

0.32

 graduated

0.32

earned

0.32

 degree

0.31

 obtained

0.31

 earning

0.30

 studying

0.30

 gradu

0.30

Activations Density 0.238%

key information related to medical professionals and their qualifications

No Comments

No Known Activations