INDEX

Explanations

references to the writing process and the experiences of writers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

edl

-0.18

oji

-0.16

 collect

-0.16

pill

-0.15

 mattresses

-0.14

iali

-0.14

 Dorm

-0.14

sz

-0.14

ebin

-0.14

åı£

-0.14

POSITIVE LOGITS

 productivity

0.32

 productive

0.26

productive

0.21

 Product

0.18

 ÑĢÐ°Ð±Ð¾Ñĩ

0.18

 PRODUCT

0.17

 Hemisphere

0.17

-product

0.17

Hem

0.17

 working

0.16

Activations Density 0.207%

references to the writing process and the experiences of writers

No Comments

No Known Activations