INDEX

Explanations

terms related to mental health topics and conditions

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

/loose

-0.15

ãĥ¼ãĤ¯

-0.15

eday

-0.15

adem

-0.15

ÏĤ

-0.15

opi

-0.14

éľŀ

-0.14

 Bened

-0.14

nown

-0.14

adar

-0.14

POSITIVE LOGITS

Ill

0.24

 illness

0.23

ill

0.23

 health

0.23

-health

0.21

 Health

0.20

 disorders

0.19

Ill

0.19

 illnesses

0.19

 disorder

0.18

Activations Density 0.010%

terms related to mental health topics and conditions

No Comments

No Known Activations