INDEX

Explanations

mentions of medical conditions and treatment methodologies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

 epidemi

-0.18

á»ĩ

-0.18

isman

-0.16

 anatom

-0.14

çĸĹ

-0.14

oxel

-0.14

arging

-0.14

è´

-0.14

linik

-0.14

 Epidemi

-0.14

POSITIVE LOGITS

 stroke

0.35

 heart

0.33

 strokes

0.32

stroke

0.30

 Stroke

0.29

 cancer

0.29

Ast

0.26

COP

0.26

 Parkinson

0.26

Stroke

0.26

Activations Density 1.087%

mentions of medical conditions and treatment methodologies

No Comments

No Known Activations