INDEX

Explanations

concepts of combination and integration across different domains or elements

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

loat

-0.18

 span

-0.17

olley

-0.15

Ð³Ð¾

-0.15

ÑģÐ»Ð¸

-0.14

legg

-0.14

rench

-0.14

vier

-0.14

 spans

-0.14

outu

-0.14

POSITIVE LOGITS

 between

0.26

 giá»¯a

0.22

 Between

0.22

 zwischen

0.22

between

0.22

 Ð¼ÐµÐ¶Ð´Ñĥ

0.20

 BETWEEN

0.20

à¸£à¸°à¸«à¸§

0.19

Between

0.18

 Ð¼ÑĸÐ¶

0.18

Activations Density 0.118%

concepts of combination and integration across different domains or elements

No Comments

No Known Activations