INDEX

Explanations

references to geographical regions, specifically in the northeastern and southeastern areas of the United States

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

Ð½Ð¸Ð½Ð°

-0.18

Ø©

-0.16

ibraltar

-0.15

Ð½Ð¸Ð½

-0.15

isor

-0.14

 Hlav

-0.14

Lit

-0.14

æµħ

-0.14

ToProps

-0.14

bum

-0.14

POSITIVE LOGITS

ern

0.56

ERN

0.36

erner

0.30

 corner

0.29

earn

0.27

corner

0.25

 quadrant

0.25

erness

0.24

ern

0.24

-corner

0.23

Activations Density 0.020%

references to geographical regions, specifically in the northeastern and southeastern areas of the United States

No Comments

No Known Activations