INDEX

Explanations

references to media elements like images and learning concepts in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

ocha

-0.17

-0.15

irit

-0.15

habi

-0.14

anium

-0.14

ufact

-0.14

abella

-0.14

usband

-0.14

eat

-0.14

uchs

-0.14

POSITIVE LOGITS

 ÎĳÎł

0.18

istrovstvÃŃ

0.16

 TELE

0.16

 inning

0.15

.twig

0.15

itte

0.14

 regional

0.14

 Regional

0.14

 Hick

0.14

ido

0.14

Activations Density 0.005%

references to media elements like images and learning concepts in various contexts

No Comments

No Known Activations