INDEX

Explanations

references to interactions and conversations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

KHR

-0.18

erosis

-0.16

lector

-0.16

ersist

-0.15

uity

-0.15

errat

-0.14

WithMany

-0.14

anners

-0.14

esti

-0.14

 Helpers

-0.14

POSITIVE LOGITS

IFIC

0.16

zd

0.15

 Liberties

0.14

inspace

0.14

indre

0.14

.TRAN

0.14

uze

0.14

 âĸº

0.14

ozÃŃ

0.13

ieren

0.13

Activations Density 0.047%

references to interactions and conversations

No Comments

No Known Activations