INDEX

Explanations

references to various types of establishments and facilities, particularly businesses and places of service

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

Ð¾ÑģÑĥÐ´

-0.17

eldon

-0.17

wort

-0.16

Ð¾ÑĢÐ°Ð·

-0.15

zek

-0.14

ELLOW

-0.14

lez

-0.14

edom

-0.14

GRA

-0.13

ÑĮÐ¼Ð¸

-0.13

POSITIVE LOGITS

 located

0.20

located

0.19

nas

0.18

bers

0.17

/library

0.17

 where

0.17

pe

0.17

 complex

0.16

/store

0.16

cum

0.16

Activations Density 0.497%

references to various types of establishments and facilities, particularly businesses and places of service

No Comments

No Known Activations