INDEX

Explanations

phrases related to warfare and military actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

alars

-0.19

aliz

-0.15

/ws

-0.15

ereo

-0.15

rok

-0.15

ÐŁÐļ

-0.14

 kontakte

-0.14

EEE

-0.14

ereco

-0.13

aland

-0.13

POSITIVE LOGITS

by

0.40

 oleh

0.29

 ØªÙĪØ³Ø·

0.28

 bá»Łi

0.27

_by

0.18

 przez

0.18

edBy

0.17

by

0.17

bv

0.15

By

0.14

Activations Density 0.786%

phrases related to warfare and military actions

No Comments

No Known Activations