INDEX

Explanations

specific geographic names and locations

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

gger

-0.17

zano

-0.17

inish

-0.16

lek

-0.15

emat

-0.15

Ley

-0.14

rouch

-0.14

esktop

-0.14

lands

-0.14

WithIdentifier

-0.14

POSITIVE LOGITS

uko

0.14

 turno

0.14

 Collective

0.14

aison

0.14

ÐºÑĥÑĢ

0.14

.enterprise

0.13

zing

0.13

anÃ©

0.13

Wer

0.13

 Roads

0.13

Activations Density 0.219%

specific geographic names and locations

No Comments

No Known Activations