INDEX

Explanations

mentions of a "catalog."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

à¸£à¸¡

-0.15

erno

-0.15

 Inflate

-0.15

ÏģÎ¿Ïį

-0.14

ì§

-0.14

å·

-0.14

zet

-0.14

á»

-0.14

Æ°á»Ŀng

-0.14

POSITIVE LOGITS

ue

0.29

ues

0.21

gue

0.20

une

0.19

ueur

0.18

UE

0.18

agar

0.17

uen

0.17

ueue

0.17

ueblo

0.17

Activations Density 0.003%

mentions of a "catalog."

No Comments

No Known Activations