INDEX

Explanations

geographical locations, specifically cities and provinces in China

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

Utf

-0.15

ailer

-0.14

anter

-0.14

Î¬Î½ÎµÎ¹

-0.14

Ð¸Ð¼Ð°

-0.14

ulet

-0.14

ersistent

-0.14

ÅĤy

-0.13

[#

-0.13

 Wisconsin

-0.13

POSITIVE LOGITS

zhou

0.34

dong

0.33

xi

0.23

Ð´Ð¾Ð½

0.20

’an

0.19

hz

0.18

gang

0.18

 Dong

0.18

don

0.18

sha

0.18

Activations Density 0.009%

geographical locations, specifically cities and provinces in China

No Comments

No Known Activations