INDEX

Explanations

descriptive attributes of places and their historical significance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

 McKay

-0.15

ouv

-0.15

oust

-0.14

 ÐºÑĥÑģÑĤ

-0.14

 Forget

-0.14

umble

-0.14

 Garr

-0.14

ervo

-0.13

Ã¤ch

-0.13

OME

-0.13

POSITIVE LOGITS

 destination

0.22

 haven

0.21

 oasis

0.21

gem

0.20

 icon

0.19

 slice

0.19

 place

0.19

destination

0.18

 Grade

0.18

hub

0.16

Activations Density 0.158%

descriptive attributes of places and their historical significance

No Comments

No Known Activations