INDEX

Explanations

elements related to styling and class attributes in code

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

ekten

-0.15

re

-0.15

avier

-0.15

Bad

-0.15

'=>['

-0.14

 bere

-0.14

habi

-0.14

fra

-0.13

Ð°Ð½Ðº

-0.13

 behalf

-0.13

POSITIVE LOGITS

íĹĮ

0.17

éĭ¼

0.17

elligence

0.15

utenberg

0.15

 ÑĢÑĸÐ´

0.14

ully

0.14

ourd

0.14

ì§ĵ

0.14

adelphia

0.14

Activations Density 0.013%

elements related to styling and class attributes in code

No Comments

No Known Activations