INDEX

Explanations

keywords and phrases related to events and their attributes in a structured data format

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 serialVersionUID

-0.16

.Void

-0.15

ÐµÐ»Ð¸Ðº

-0.15

OperationException

-0.14

_DIAG

-0.14

à¸ļà¸ļ

-0.14

ajan

-0.14

venta

-0.14

 Dissertation

-0.14

andas

-0.14

POSITIVE LOGITS

do

0.52

do

0.38

do

0.32

Do

0.26

Do

0.26

 does

0.24

.do

0.22

did

0.21

 Ð´Ð¾

0.19

-do

0.19

Activations Density 0.006%

keywords and phrases related to events and their attributes in a structured data format

No Comments

No Known Activations