INDEX

Explanations

distances and measurements related to location

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

zych

-0.18

afen

-0.16

 massa

-0.15

borg

-0.14

 Moss

-0.14

undy

-0.14

McG

-0.14

ledge

-0.14

bote

-0.14

Ð°Ð½Ð´

-0.13

POSITIVE LOGITS

 miles

0.74

 mile

0.70

 Miles

0.65

-mile

0.61

km

0.56

 mileage

0.56

 Mile

0.55

 kilometers

0.53

mile

0.52

km

0.52

Activations Density 0.186%

distances and measurements related to location

No Comments

No Known Activations

distances and measurements related to location

No Comments

No Known Activations