INDEX

Explanations

expressions related to emergency situations and responses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

_busy

-0.18

Unnamed

-0.15

cez

-0.14

venir

-0.14

redient

-0.14

trinsic

-0.14

æİ§

-0.13

.epsilon

-0.13

rikes

-0.13

oram

-0.13

POSITIVE LOGITS

 evacuation

0.46

 evac

0.43

 evacuate

0.40

 evacuated

0.39

Ev

0.31

 shelter

0.30

-ev

0.29

Ev

0.28

ev

0.25

 Shelter

0.25

Activations Density 0.062%

expressions related to emergency situations and responses

No Comments

No Known Activations

expressions related to emergency situations and responses

No Comments

No Known Activations