INDEX

Explanations

references to regulations and human experiences related to firearms or personal finance

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

-0.44

---

-0.36

 -↵

-0.35

 -↵↵

-0.33

—

-0.33

 —↵

-0.30

 ---↵

-0.29

 ãĢľ

-0.28

 âĢĲ

-0.28

 âĪĴ

-0.25

POSITIVE LOGITS

–

0.56

–and

0.45

–↵↵

0.43

.–

0.34

Âĸ

0.31

 Ø¨ÙĢ

0.27

->

0.27

--

0.27

 ()=>

0.24

--[

0.23

Activations Density 0.039%

references to regulations and human experiences related to firearms or personal finance

No Comments

No Known Activations