INDEX

Explanations

structures and symbols used in code, particularly related to syntax and programming constructs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

_)↵

-0.30

 "")↵

-0.26

 )↵

-0.25

())↵

-0.25

()")↵

-0.25

')↵

-0.25

)')↵

-0.25

`)↵

-0.24

$")↵

-0.24

!)↵

-0.24

POSITIVE LOGITS

};↵↵

0.49

};

0.48

 };↵↵

0.48

};↵

0.48

};

0.47

 };↵

0.47

};↵↵↵

0.41

 };↵↵↵

0.40

];

0.38

);

0.37

Activations Density 0.151%

structures and symbols used in code, particularly related to syntax and programming constructs

No Comments

No Known Activations