INDEX

Explanations

references to historical figures and their contributions

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

uing

-0.17

_iff

-0.15

cio

-0.15

xFFFFFF

-0.15

ļ

-0.14

ells

-0.14

exc

-0.14

ics

-0.14

Ø¹Ø§

-0.14

 christ

-0.14

POSITIVE LOGITS

awi

0.23

iyat

0.23

qli

0.22

noon

0.21

rou

0.21

leh

0.21

heed

0.21

qa

0.21

arah

0.21

heel

0.20

Activations Density 0.131%

references to historical figures and their contributions

No Comments

No Known Activations