INDEX

Explanations

dialogue and conversational phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

doch

-0.16

ÄŁan

-0.15

ahir

-0.15

antz

-0.15

 theirs

-0.14

loff

-0.14

ÐĲÑĢÑħÑĸÐ²

-0.14

Î»Î¹Î¿

-0.14

 Noon

-0.14

ogan

-0.14

POSITIVE LOGITS

0.14

din

0.14

eb

0.14

Wax

0.13

é³

0.13

asia

0.13

âĢ¦

0.13

QUI

0.13

èį

0.12

 Caul

0.12

Activations Density 2.205%

dialogue and conversational phrases

No Comments

No Known Activations