INDEX

Explanations

technical terms and parameters related to programming and data handling

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

adero

-0.15

ickerView

-0.15

Ry

-0.15

-addons

-0.15

ÏģÎ¯

-0.14

/py

-0.13

ÑĢÐ¾ÑĪ

-0.13

ream

-0.13

ellipsis

-0.13

POSITIVE LOGITS

do

0.30

 unless

0.28

 rescue

0.25

||

0.23

.to

0.22

Nit

0.21

do

0.21

nil

0.20

unless

0.20

 ||↵

0.19

Activations Density 0.022%

technical terms and parameters related to programming and data handling

No Comments

No Known Activations