INDEX

Explanations

commands or calls to action

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

gaard

-0.19

 Ashe

-0.14

gon

-0.14

usc

-0.14

Bitte

-0.14

 ÐŁÑĢÐ°

-0.14

ult

-0.14

 ultimate

-0.13

InBackground

-0.13

POSITIVE LOGITS

 Sherlock

0.17

alara

0.17

Ã¡du

0.15

Î´Î±

0.15

unos

0.15

_Tis

0.14

Ã§u

0.14

rets

0.14

Ø§Ø¯Ùĩ

0.14

utenberg

0.13

Activations Density 0.045%

commands or calls to action

No Comments

No Known Activations