INDEX

Explanations

mentions of brands or products related to motorcycles and safety gear

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

Ð²Ð¾Ð»Ñı

-0.14

Î»Î¹ÎºÎ¬

-0.13

 Nass

-0.13

fragistics

-0.12

blah

-0.12

Ã¡zd

-0.12

llib

-0.12

ãĥ³ãĥĸ

-0.12

ìĿ¸íĬ¸

-0.12

ascar

-0.12

POSITIVE LOGITS

Hen

0.60

hen

0.59

len

0.57

HEN

0.57

hen

0.57

len

0.56

Jen

0.56

ken

0.56

Hen

0.56

zen

0.56

Activations Density 0.357%

mentions of brands or products related to motorcycles and safety gear

No Comments

No Known Activations