INDEX

Explanations

terms related to safety and precautions in a workplace context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

.community

-0.16

abwe

-0.15

 NavParams

-0.14

ARGER

-0.14

agate

-0.14

 COMPUTER

-0.14

ibble

-0.14

.dtd

-0.14

/format

-0.14

bach

-0.14

POSITIVE LOGITS

 safety

0.32

 Safety

0.29

 workplace

0.28

Safety

0.27

 unsafe

0.26

 worker

0.25

 work

0.25

 hazards

0.24

afety

0.23

 workers

0.23

Activations Density 0.121%

terms related to safety and precautions in a workplace context

No Comments

No Known Activations