INDEX

Explanations

specific terms and metrics related to digital content and online interactions

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

ussen

-0.19

æ¦Ĥ

-0.15

Ranked

-0.15

BOVE

-0.15

askan

-0.14

_checked

-0.14

 Identified

-0.14

 expanded

-0.14

 Programming

-0.13

Scoped

-0.13

POSITIVE LOGITS

 being

0.31

 happening

0.29

 done

0.29

being

0.28

 undertaken

0.27

 available

0.27

 performed

0.26

 conducted

0.26

 currently

0.25

 underway

0.24

Activations Density 0.022%

specific terms and metrics related to digital content and online interactions

No Comments

No Known Activations