INDEX

Explanations

phrases and terms related to health issues, especially regarding symptoms and medications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

ppard

-0.15

 Joint

-0.15

vel

-0.15

onal

-0.14

tres

-0.14

å¾Ĵ

-0.14

elig

-0.14

 vibr

-0.14

Ps

-0.13

leg

-0.13

POSITIVE LOGITS

 nausea

0.33

vom

0.31

 vomiting

0.30

 nause

0.28

 stomach

0.22

åĲĲ

0.18

 sickness

0.17

aukee

0.15

 dizzy

0.15

ickness

0.14

Activations Density 0.046%

phrases and terms related to health issues, especially regarding symptoms and medications

No Comments

No Known Activations