INDEX

Explanations

terms related to occupational safety and health regulations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

rippling

-0.17

hiba

-0.15

adÃŃ

-0.15

agnost

-0.15

_advanced

-0.14

EFI

-0.14

peater

-0.14

avig

-0.14

ordinated

-0.14

LookAndFeel

-0.13

POSITIVE LOGITS

 workplace

0.16

 safety

0.16

 Industrial

0.16

MEP

0.16

Safety

0.15

 industrial

0.15

 Safety

0.15

å·¥

0.15

Industrial

0.15

 Damon

0.15

Activations Density 0.068%

terms related to occupational safety and health regulations

No Comments

No Known Activations