INDEX

Explanations

expressions related to prescription medications and their effects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

aurus

-0.16

eration

-0.15

imler

-0.15

cÃ¼

-0.14

erset

-0.14

Alchemy

-0.14

ãĥ³ãĥĩ

-0.14

oure

-0.14

 Miles

-0.14

iye

-0.14

POSITIVE LOGITS

 tablets

0.32

 pills

0.31

 medication

0.31

 meds

0.29

-pill

0.28

 aspir

0.27

 tablet

0.26

 prescribed

0.25

 Tablets

0.25

 medications

0.25

Activations Density 0.361%

expressions related to prescription medications and their effects

No Comments

No Known Activations