INDEX

Explanations

terms related to measurements and biases in technical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

ÏĥÎ¯Î±

-0.15

 âĤ¹

-0.15

readcr

-0.14

 è±

-0.13

 Hyper

-0.13

OptionPane

-0.13

.Emit

-0.13

reek

-0.13

oley

-0.13

 è©ķ

-0.13

POSITIVE LOGITS

Fal

0.42

Fal

0.35

 practitioner

0.30

 practitioners

0.30

 Pract

0.26

fal

0.24

fal

0.23

 cultivation

0.23

CCP

0.22

 cultiv

0.22

Activations Density 0.004%

terms related to measurements and biases in technical contexts

No Comments

No Known Activations