INDEX

Explanations

references to lakes and bodies of water

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

 Coastal

-0.22

 coastal

-0.21

 seaside

-0.16

 Tide

-0.16

Lei

-0.16

bjerg

-0.15

å»Ĭ

-0.14

 desert

-0.14

 Ocean

-0.14

 subjects

-0.14

POSITIVE LOGITS

 lake

0.67

 Lake

0.63

Lake

0.60

æ¹ĸ

0.54

lake

0.53

 lakes

0.50

 Lakes

0.45

 æ¹ĸ

0.41

lak

0.40

 Ð¾Ð·

0.38

Activations Density 0.148%

references to lakes and bodies of water

No Comments

No Known Activations