INDEX

Explanations

references to healthcare-related statistics and trends

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

enu

-0.16

ARA

-0.16

ior

-0.15

by

-0.15

oor

-0.15

-0.14

 outcome

-0.14

og

-0.14

oun

-0.14

ere

-0.14

POSITIVE LOGITS

 number

0.33

 figure

0.27

 proportion

0.25

number

0.23

 average

0.23

figure

0.22

 share

0.22

 figures

0.21

 median

0.21

 total

0.20

Activations Density 0.168%

references to healthcare-related statistics and trends

No Comments

No Known Activations