INDEX

Explanations

numerical identifiers or codes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

../../../

-0.17

à¤²

-0.17

uish

-0.16

airo

-0.15

amet

-0.15

à¸Ĭ

-0.15

-quarters

-0.15

vise

-0.15

engin

-0.15

action

-0.15

POSITIVE LOGITS

ties

0.24

ãģĤãģ£ãģŁ

0.23

teenth

0.22

0.20

-os

0.19

athon

0.19

0.18

wich

0.15

hell

0.15

TY

0.15

Activations Density 0.310%

numerical identifiers or codes

No Comments

No Known Activations