INDEX

Explanations

mathematical symbols and functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

ģµ

-0.17

isp

-0.15

Chan

-0.14

/of

-0.14

 îł

-0.13

isiyle

-0.13

-central

-0.13

ousel

-0.13

chan

-0.13

uali

-0.13

POSITIVE LOGITS

_{

0.28

}_{

0.20

 subscript

0.20

$_

0.18

$_

0.18

_{

0.17

echa

0.15

'_

0.15

kea

0.15

&_

0.14

Activations Density 0.212%

mathematical symbols and functions

No Comments

No Known Activations