INDEX

Explanations

details about vehicle design and features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

å¼¹

-0.16

Gib

-0.16

crast

-0.15

ÑĸÐ±

-0.14

 mekan

-0.14

earer

-0.14

pink

-0.14

ocale

-0.14

oader

-0.14

primir

-0.14

POSITIVE LOGITS

 grille

0.26

 spoiler

0.24

 grill

0.22

 Grill

0.22

 honey

0.20

 Harmon

0.19

 rear

0.19

aer

0.18

 chrome

0.18

Xen

0.18

Activations Density 0.042%

details about vehicle design and features

No Comments

No Known Activations