INDEX

Explanations

detailed descriptions of physical attributes and measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

 cube

-0.16

ijo

-0.15

 cubes

-0.15

 Cube

-0.14

.getActive

-0.14

filters

-0.13

 Jerome

-0.13

çģµ

-0.13

Cub

-0.13

POSITIVE LOGITS

 marks

0.27

gro

0.24

 tracks

0.23

 mark

0.22

 indent

0.21

 groove

0.21

marks

0.20

 impressions

0.20

tracks

0.20

 Tracks

0.20

Activations Density 0.130%

detailed descriptions of physical attributes and measurements

No Comments

No Known Activations