INDEX

Explanations

numbers and numerical data points

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

\OptionsResolver

-0.15

yz

-0.15

argas

-0.14

tplib

-0.14

ãĥ³ãĥĢ

-0.13

uda

-0.13

 buflen

-0.13

è

-0.13

ÑĨÐµÑĢ

-0.13

POSITIVE LOGITS

ched

0.18

intree

0.17

uet

0.16

lÃ¡d

0.15

livÄĽ

0.15

Äĥn

0.15

aine

0.15

GRES

0.14

isma

0.14

lij

0.14

Activations Density 0.040%

numbers and numerical data points

No Comments

No Known Activations