INDEX

Explanations

mentions of New Zealand

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

Moj

-0.19

bsp

-0.16

oru

-0.15

alice

-0.15

utow

-0.15

ubl

-0.15

ãĥĭãĥĥãĤ¯

-0.14

ortal

-0.14

rio

-0.14

inyin

-0.14

POSITIVE LOGITS

Ze

0.34

 Zealand

0.33

Ze

0.33

ze

0.30

ze

0.25

ZE

0.24

 zeal

0.23

-Z

0.23

 Guinea

0.22

stalk

0.22

Activations Density 0.009%

mentions of New Zealand

No Comments

No Known Activations