INDEX

Explanations

numerical data and statistical information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ients

-0.15

ãĥ¼ãĥĢ

-0.15

enschaft

-0.14

 aray

-0.14

isz

-0.14

qml

-0.14

obody

-0.14

},

-0.13

vironment

-0.13

emez

-0.13

POSITIVE LOGITS

)(

0.17

tlement

0.15

-Javadoc

0.14

REA

0.14

ceased

0.14

ãĥªãĤ¢

0.14

 Surround

0.13

ÑįÑĤÐ¾Ð¼Ñĥ

0.13

_restrict

0.13

acco

0.13

Activations Density 0.189%

numerical data and statistical information

No Comments

No Known Activations

numerical data and statistical information

No Comments

No Known Activations