INDEX

Explanations

elements related to programming or markup syntax

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ampa

-0.17

Ð¾Ð´Ð°Ð²

-0.16

inders

-0.15

overy

-0.15

Ã¢t

-0.14

 entr

-0.14

vap

-0.14

ise

-0.14

_ASM

-0.14

herits

-0.14

POSITIVE LOGITS

Å

0.15

prop

0.15

umed

0.14

ymm

0.14

ADE

0.14

à¸Ļà¸Ń

0.14

ymmetric

0.14

por

0.13

 mamma

0.13

osite

0.13

Activations Density 0.017%

elements related to programming or markup syntax

No Comments

No Known Activations