INDEX

Explanations

references to lockdown measures related to the COVID-19 pandemic

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

.scalablytyped

-0.25

yscale

-0.17

.nano

-0.17

erva

-0.16

eniz

-0.15

zahl

-0.14

ervo

-0.14

 Saud

-0.13

isson

-0.13

offs

-0.13

POSITIVE LOGITS

 Steele

0.15

ZF

0.15

Tie

0.15

ary

0.14

tie

0.14

WP

0.14

panic

0.13

ÙĨØ´

0.13

expo

0.13

(AT

0.13

Activations Density 0.006%

references to lockdown measures related to the COVID-19 pandemic

No Comments

No Known Activations