INDEX

Explanations

references to images or pictures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

oli

-0.17

shot

-0.16

Ùĳ

-0.15

cribed

-0.15

ster

-0.15

ika

-0.15

ä¿Ĺ

-0.15

isi

-0.15

hn

-0.15

shire

-0.14

POSITIVE LOGITS

ocks

0.18

iban

0.17

orial

0.17

ASTE

0.15

ofday

0.15

-per

0.15

auf

0.15

askell

0.15

 Yates

0.14

getter

0.14

Activations Density 0.040%

references to images or pictures

No Comments

No Known Activations