INDEX

Explanations

references to COVID-19 variants

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

 Prim

-0.17

ease

-0.16

uhl

-0.14

áº¡nh

-0.14

aviest

-0.14

 prim

-0.14

enton

-0.14

-0.13

isque

-0.13

xbf

-0.13

POSITIVE LOGITS

ocl

0.15

 Niet

0.15

|unique

0.14

à¸±à¸ĩà¸Ħ

0.14

ovel

0.14

TRACT

0.14

Ð¾Ð»Ñı

0.14

us

0.14

 existing

0.13

acet

0.13

Activations Density 0.006%

references to COVID-19 variants

No Comments

No Known Activations