INDEX

Explanations

comments and documentation elements within code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 Inherits

-0.17

 Uncomment

-0.17

åī£

-0.14

oo

-0.14

eland

-0.13

 Initialise

-0.13

 Invalidate

-0.13

dur

-0.13

mob

-0.13

hits

-0.13

POSITIVE LOGITS

 Convenience

0.28

 convenience

0.25

 returns

0.22

 Returns

0.21

 helper

0.20

 Helper

0.19

 Return

0.18

-helper

0.18

 retour

0.18

Helper

0.18

Activations Density 0.084%

comments and documentation elements within code

No Comments

No Known Activations