INDEX

Explanations

references to locations and addresses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

iens

-0.17

_FALL

-0.16

 sÃ¡t

-0.15

gorm

-0.15

ordion

-0.14

hci

-0.14

æ©

-0.14

.AttributeSet

-0.13

 colleg

-0.13

 Disclosure

-0.13

POSITIVE LOGITS

 Denver

0.25

Denver

0.23

 Broncos

0.19

 Aurora

0.18

 Stap

0.18

 Arap

0.17

 Nuggets

0.17

Rox

0.17

 Greenwood

0.17

 Seah

0.16

Activations Density 0.059%

references to locations and addresses

No Comments

No Known Activations