INDEX

Explanations

descriptive phrases related to notable places and landmarks

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

iÃ¨res

-0.17

ervo

-0.16

oun

-0.16

 Lobby

-0.15

oust

-0.14

omes

-0.14

aps

-0.14

abin

-0.14

ml

-0.14

 ÐºÑĥÑģÑĤ

-0.14

POSITIVE LOGITS

 place

0.23

 institution

0.22

 venue

0.21

 destination

0.21

 facility

0.21

facility

0.19

gem

0.19

destination

0.19

 haven

0.19

gems

0.18

Activations Density 0.194%

descriptive phrases related to notable places and landmarks

No Comments

No Known Activations