INDEX

Explanations

references to healthcare workers and their experiences during crises

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

liner

-0.16

unuz

-0.14

.DOM

-0.14

alfa

-0.14

 Hyde

-0.14

inois

-0.14

uyen

-0.13

-ÑĤÐ¾

-0.13

æľĹ

-0.13

à¸²à¸į

-0.13

POSITIVE LOGITS

 during

0.44

during

0.39

 durante

0.38

 During

0.37

During

0.36

 wÃ¤hrend

0.29

 bÄĽhem

0.27

 pandemic

0.25

WW

0.25

 COVID

0.23

Activations Density 0.250%

references to healthcare workers and their experiences during crises

No Comments

No Known Activations