INDEX

Explanations

references to treatment and withdrawal symptoms related to alcohol and drug abuse

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

 DÃ¼n

-0.16

orian

-0.15

sand

-0.15

à¤Ĺà¤²

-0.14

ë¯

-0.14

erb

-0.14

à¸ķà¸£

-0.13

SGlobal

-0.13

indsight

-0.13

POSITIVE LOGITS

 withdrawal

0.36

 Withdraw

0.34

 quit

0.34

 withdrawals

0.31

 withdraw

0.30

 quits

0.29

Withdraw

0.29

 Quit

0.29

 quitting

0.29

 taper

0.28

Activations Density 0.024%

references to treatment and withdrawal symptoms related to alcohol and drug abuse

No Comments

No Known Activations