INDEX

Explanations

names and references to various individuals or characters

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

reds

-0.16

vern

-0.16

éĺħè¯»æ¬¡æķ°

-0.15

canf

-0.15

oller

-0.15

Ø¸ÙħØ©

-0.14

arendra

-0.14

 otom

-0.14

ietet

-0.14

/Set

-0.14

POSITIVE LOGITS

aur

0.26

 Mein

0.24

hai

0.23

py

0.23

ho

0.22

Aur

0.22

 matlab

0.22

Py

0.21

 mere

0.21

 Maine

0.20

Activations Density 0.065%

names and references to various individuals or characters

No Comments

No Known Activations