INDEX

Explanations

links to articles or stories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

iton

-0.18

Eh

-0.18

-0.17

thon

-0.15

eh

-0.15

 Wing

-0.14

ber

-0.14

otty

-0.14

ift

-0.14

POSITIVE LOGITS

rema

0.16

Ø®Ø§ÙĨÙĩ

0.16

ivamente

0.15

ambre

0.15

AVA

0.14

itech

0.14

ÙĪØ¬Ùĩ

0.14

 ëĦ

0.14

Ð´Ð°Ð¿

0.14

ëł

0.14

Activations Density 0.003%

links to articles or stories

No Comments

No Known Activations