INDEX

Explanations

references to legal regulations and public safety issues

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

unami

-0.14

iben

-0.14

utzer

-0.14

-fed

-0.14

onical

-0.14

Ø±Ø²

-0.13

ÏģÎ·

-0.13

çł²

-0.13

iffe

-0.13

Cre

-0.13

POSITIVE LOGITS

 driving

0.33

 Driving

0.33

 drunk

0.30

DUI

0.30

 alcohol

0.29

 breath

0.28

 Breath

0.28

Driving

0.28

 impaired

0.28

 impairment

0.27

Activations Density 0.029%

references to legal regulations and public safety issues

No Comments

No Known Activations