INDEX

Explanations

structured elements of code and error handling

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

%,

-0.15

raq

-0.15

uye

-0.15

 Schro

-0.15

Ø§Ø¯Øª

-0.14

ocre

-0.14

âĢ³E

-0.14

?',

-0.14

wich

-0.14

awning

-0.14

POSITIVE LOGITS

0.23

//

0.23

0.22

--

0.20

0.19

0.18

0.17

...

0.17

Activations Density 0.164%

structured elements of code and error handling

No Comments

No Known Activations