INDEX

Explanations

technical terms and concepts related to engineering or mechanical processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

ÑĸÐ½ÑĮ

-0.16

ØŃÙĦ

-0.15

Î¬Î½Î¹

-0.15

irable

-0.15

appable

-0.14

Toolkit

-0.14

.gdx

-0.13

 Pret

-0.13

 nowrap

-0.13

assen

-0.13

POSITIVE LOGITS

 prior

0.35

prior

0.32

 Prior

0.31

Prior

0.29

art

0.29

 teachings

0.28

 disclosures

0.25

_prior

0.24

 known

0.24

 skilled

0.23

Activations Density 0.097%

technical terms and concepts related to engineering or mechanical processes

No Comments

No Known Activations