INDEX

Explanations

technical terms and concepts related to engineering or mechanics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

 Covered

-0.23

 covered

-0.19

åıĹ

-0.18

covered

-0.18

lad

-0.16

ested

-0.16

ÑĢÑĥ

-0.15

 kabil

-0.15

Accepted

-0.15

 inhabited

-0.15

POSITIVE LOGITS

 arranged

0.36

 array

0.29

 placed

0.29

 laid

0.29

arr

0.26

 spread

0.24

 arrange

0.24

 attached

0.23

 organized

0.23

 mounted

0.23

Activations Density 0.233%

technical terms and concepts related to engineering or mechanics

No Comments

No Known Activations