INDEX

Explanations

instances of numerical values and associated dashes or symbols

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

–

-0.40

--

-0.30

 –↵

-0.28

 –↵↵

-0.28

">--}}↵

-0.24

)--

-0.23

 --↵

-0.23

--

-0.23

âĶĢâĶĢ

-0.21

.--

-0.20

POSITIVE LOGITS

————————————————

0.50

————————

0.46

————

0.43

——

0.39

—

0.29

0.28

—

0.28

âĢī

0.27

 —↵↵

0.24

âĢĬ

0.24

Activations Density 0.049%

instances of numerical values and associated dashes or symbols

No Comments

No Known Activations