INDEX

Explanations

terms related to chronic diseases and their characteristics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

 rein

-0.15

apse

-0.14

ustomer

-0.14

Ãºng

-0.14

 crashed

-0.14

éĢ¸

-0.13

adera

-0.13

ulton

-0.13

 Martinez

-0.13

POSITIVE LOGITS

 treat

0.24

 progressive

0.21

 condition

0.21

cur

0.19

unt

0.19

 incur

0.18

 characterized

0.18

 Treat

0.18

 caused

0.18

lif

0.18

Activations Density 0.058%

terms related to chronic diseases and their characteristics

No Comments

No Known Activations