INDEX

Explanations

symbols or special characters

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

 Leipzig

-0.20

 Dresden

-0.17

 GmbH

-0.17

 Cologne

-0.17

Ã¶tt

-0.17

 Slovenia

-0.16

 Stuttgart

-0.16

 Nylon

-0.15

resden

-0.15

 Analyst

-0.15

POSITIVE LOGITS

 Bere

0.40

 Tacoma

0.39

 Northwest

0.32

 Seattle

0.32

 Spokane

0.31

Seattle

0.28

WA

0.28

bere

0.28

Ed

0.27

 Pacific

0.27

Activations Density 0.004%

symbols or special characters

No Comments

No Known Activations