INDEX

Explanations

numerical data or statistics related to image popularity

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

enstein

-0.16

-0.15

bour

-0.14

 chez

-0.14

ap

-0.14

-0.13

 calculus

-0.13

_continuous

-0.13

earer

-0.13

POSITIVE LOGITS

urette

0.17

AGMENT

0.15

ãĤ·ãĤ¢

0.14

/qt

0.14

adÄ±k

0.14

íļį

0.14

-placeholder

0.13

nÃ¡m

0.13

avage

0.13

dings

0.13

Activations Density 0.005%

numerical data or statistics related to image popularity

No Comments

No Known Activations