INDEX

Explanations

punctuation marks and characters often used in code or programming statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

Orr

-0.17

/REC

-0.17

-0.16

/Foundation

-0.14

 Ð¿Ð¾Ð²

-0.14

grave

-0.14

ãĥ³ãĥĸ

-0.14

POSITIVE LOGITS

0.44

0.40

0.30

0.28

↵                    ↵

0.25

↵

0.25

--------------------

0.24

                    č↵

0.23

Activations Density 0.006%

punctuation marks and characters often used in code or programming statements

No Comments

No Known Activations