INDEX

Explanations

references to simplicity

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

_headers

-0.17

íĶ¼

-0.16

age

-0.15

ãĥ¼ãĤ¯

-0.14

uyen

-0.14

itia

-0.14

ance

-0.14

end

-0.13

idious

-0.13

ajor

-0.13

POSITIVE LOGITS

artner

0.21

ÐµÐ»ÑĮÐ·Ñı

0.18

ELY

0.17

ditor

0.15

psz

0.15

azzo

0.14

ettel

0.14

itzer

0.14

.deleteById

0.13

siz

0.13

Activations Density 0.003%

references to simplicity

No Comments

No Known Activations