INDEX

Explanations

terms related to the COVID-19 pandemic and health measures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

quina

-0.18

eniz

-0.16

inkle

-0.15

Å¡ka

-0.15

 mold

-0.15

 tort

-0.15

 Nurs

-0.15

Ã¤nn

-0.14

elerik

-0.14

 embry

-0.14

POSITIVE LOGITS

 Oxygen

0.22

 districts

0.20

 oxygen

0.20

Union

0.19

RTP

0.19

cor

0.19

Cov

0.19

 Union

0.18

Kov

0.18

 district

0.17

Activations Density 0.016%

terms related to the COVID-19 pandemic and health measures

No Comments

No Known Activations