INDEX

Explanations

geographical references 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 @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

Ð¾ÐºÐ°

-0.17

ilateral

-0.15

oden

-0.15

 Giang

-0.15

 Liga

-0.14

ntag

-0.14

à¸±à¸Ĺ

-0.14

duk

-0.14

.central

-0.14

okt

-0.14

POSITIVE LOGITS

 Tours

0.33

 Nice

0.33

 Nancy

0.32

Nice

0.28

 Cler

0.26

 Antib

0.26

 Vers

0.25

 Chart

0.25

 Dunk

0.25

Gap

0.24

Activations Density 0.114%

geographical references and locations

No Comments

No Known Activations