INDEX

Explanations

technical terms related to data encoding and processing

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

 Goldberg

-0.22

 Crowley

-0.22

 Harding

-0.20

 Armstrong

-0.20

 Bowie

-0.20

 Wright

-0.19

 Wichita

-0.19

 Birmingham

-0.19

 McConnell

-0.19

 Jennings

-0.18

POSITIVE LOGITS

 Hayward

0.26

 Alexandra

0.23

 Irvine

0.23

Ī

0.23

0.21

 Willis

0.21

 Nunes

0.21

 Suzanne

0.21

Activations Density 0.113%

technical terms related to data encoding and processing

No Comments

No Known Activations