INDEX

Explanations

documentation comments in code

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

‘

-0.17

‘

-0.17

.âĢ¦↵↵

-0.16

âĢ¦"

-0.15

)`

-0.14

`\

-0.14

}`

-0.14

Âĳ

-0.14

âĢ¦I

-0.13

âĢ¦)

-0.13

POSITIVE LOGITS

{@

0.37

{@

0.34

.java

0.27

 java

0.26

 serialVersionUID

0.26

 Java

0.26

'{@

0.26

Java

0.24

JDK

0.24

java

0.23

Activations Density 0.045%

documentation comments in code

No Comments

No Known Activations