INDEX

Explanations

mentions of "Iron" and related terms associated with the Iron Man character or concept

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

omor

-0.16

urs

-0.16

á»Ĩ

-0.15

Ã¢t

-0.15

dle

-0.15

ourn

-0.15

unas

-0.14

ermo

-0.14

led

-0.14

ums

-0.14

POSITIVE LOGITS

ically

0.28

mong

0.25

ore

0.24

 Maiden

0.24

workers

0.23

cl

0.22

 maiden

0.22

 filings

0.20

worker

0.20

ical

0.20

Activations Density 0.010%

mentions of "Iron" and related terms associated with the Iron Man character or concept

No Comments

No Known Activations