INDEX

Explanations

specific numerical data and metrics related to content engagement or feedback

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

 wire

-0.15

ãĤ¤ãĥ³

-0.14

quot

-0.14

wire

-0.14

äºĭ

-0.14

letcher

-0.14

chema

-0.14

ter

-0.14

 Wire

-0.14

retty

-0.14

POSITIVE LOGITS

ubat

0.18

embre

0.17

ÑĥÑĤÑĮ

0.15

 Ø·Ø¨ÙĬ

0.15

/commons

0.14

itas

0.13

anship

0.13

/UIKit

0.13

":[{↵

0.13

pei

0.13

Activations Density 0.030%

specific numerical data and metrics related to content engagement or feedback

No Comments

No Known Activations