INDEX

Explanations

features related to significant achievements or rankings

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

ibil

-0.16

igsaw

-0.16

kart

-0.15

ahat

-0.14

odore

-0.14

kul

-0.14

(from

-0.13

 Ober

-0.13

asar

-0.13

aghetti

-0.13

POSITIVE LOGITS

Ø¯Ø§ÙĨ

0.16

å¹

0.15

yor

0.15

wi

0.15

 Hanna

0.14

 jenter

0.14

SED

0.14

ãİ¡

0.14

uv

0.14

ë¦¬ìĸ´

0.14

Activations Density 0.263%

features related to significant achievements or rankings

No Comments

No Known Activations