INDEX

Explanations

terms and phrases related to mental health conditions and treatments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

/Dk

-0.16

Ã¡vÄĽ

-0.15

à¤¹à¤°

-0.14

ensing

-0.14

ulnerable

-0.14

iol

-0.13

foy

-0.13

borrow

-0.13

otts

-0.13

ottle

-0.13

POSITIVE LOGITS

ailability

0.16

WARDED

0.15

ãĤ¯ãĥĪ

0.14

kee

0.14

Å¡ak

0.14

 Capac

0.14

ontent

0.14

sav

0.14

ailable

0.13

BoxLayout

0.13

Activations Density 0.038%

terms and phrases related to mental health conditions and treatments

No Comments

No Known Activations