INDEX

Explanations

references to parking facilities and locations

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

-0.15

ÑģÑĤÐ²

-0.15

UILDER

-0.14

ixo

-0.14

pler

-0.14

ÅŁk

-0.14

 kÃ¥

-0.13

 Marketing

-0.13

POSITIVE LOGITS

lot

0.41

lot

0.35

Lot

0.33

Lot

0.31

 garage

0.31

_lot

0.28

LOT

0.26

 Garage

0.23

.lot

0.23

gar

0.21

Activations Density 0.013%

references to parking facilities and locations

No Comments

No Known Activations