INDEX

Explanations

expressions and variables related to mathematical formulations and equations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

Ã¥l

-0.15

 ÃĤ

-0.14

bul

-0.14

Ð¼ÑĸÐ½

-0.14

cks

-0.14

fat

-0.13

 Junk

-0.13

ch

-0.13

 prop

-0.13

 ï¿½ï¿½ï¿½ï¿½

-0.13

POSITIVE LOGITS

_{

0.47

_č↵

0.27

_{

0.26

}_{

0.23

_↵

0.21

_↵↵

0.18

_%

0.18

kehr

0.16

'_

0.16

_|

0.16

Activations Density 0.076%

expressions and variables related to mathematical formulations and equations

No Comments

No Known Activations