INDEX

Explanations

terms related to documentation and instructional content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

innacle

-0.15

pte

-0.15

esseract

-0.14

 Inventory

-0.14

Inventory

-0.14

ityEngine

-0.14

Ã¡mara

-0.14

_RENDERER

-0.13

 diffusion

-0.13

vo

-0.13

POSITIVE LOGITS

FAQ

0.23

 overview

0.20

FAQ

0.20

faq

0.20

 introduction

0.20

_intro

0.19

 Trou

0.18

 Getting

0.18

How

0.18

ysz

0.17

Activations Density 0.113%

terms related to documentation and instructional content

No Comments

No Known Activations