INDEX

Explanations

references to free offers or giveaways

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

å¶

-0.16

 intact

-0.15

Envelope

-0.15

 occasion

-0.15

 gider

-0.15

ug

-0.14

esini

-0.14

alli

-0.14

resolved

-0.14

Ð½Ð°ÑĢ

-0.13

POSITIVE LOGITS

bie

0.20

bies

0.19

RTOS

0.17

icular

0.16

ze

0.16

azon

0.15

iset

0.15

å¹ķ

0.14

zes

0.14

edom

0.14

Activations Density 0.029%

references to free offers or giveaways

No Comments

No Known Activations