INDEX

Explanations

references to medical and health-related topics, particularly concerning coronavirus

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

/workspace

-0.16

æ³Ĭ

-0.15

áº£nh

-0.15

apus

-0.14

esin

-0.14

áº¥u

-0.13

placer

-0.13

(IDC

-0.13

emek

-0.13

rouch

-0.13

POSITIVE LOGITS

 mRNA

0.27

 mandates

0.24

 Fauc

0.24

 injections

0.24

jab

0.24

 Gates

0.23

 experimental

0.23

 totalitarian

0.23

 Klaus

0.23

Fa

0.23

Activations Density 0.011%

references to medical and health-related topics, particularly concerning coronavirus

No Comments

No Known Activations