INDEX

Explanations

references to diabetes and related medical terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ivent

-0.17

aning

-0.15

lop

-0.15

EIF

-0.15

 ÑĤÑĢÐ°Ð²

-0.14

orio

-0.14

igne

-0.14

lige

-0.14

anh

-0.14

EW

-0.14

POSITIVE LOGITS

 mell

0.44

 Mell

0.36

abetes

0.22

 diabetes

0.20

 ç³

0.20

 sweet

0.20

zend

0.20

 Sweet

0.19

Sugar

0.19

 glucose

0.19

Activations Density 0.005%

references to diabetes and related medical terms

No Comments

No Known Activations