INDEX

Explanations

connections to specific locations and events in a community context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ÑĶÐ¼

-0.16

jin

-0.14

à¥ĩà¤¡

-0.14

 ëĮĢêµ¬

-0.14

issippi

-0.14

 Sabha

-0.14

ÙģØ±Ø§ÙĨ

-0.14

 Draco

-0.14

è¡Ĩ

-0.14

enville

-0.14

POSITIVE LOGITS

 Arlington

0.35

 Fairfax

0.29

 Alexandria

0.29

 Ross

0.25

 Loud

0.24

 Shir

0.24

 Rest

0.23

 Northern

0.22

 Vienna

0.22

Activations Density 0.021%

connections to specific locations and events in a community context

No Comments

No Known Activations