INDEX

Explanations

references to programming concepts and code-related terms

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

fts

-0.16

ieres

-0.16

ell

-0.15

 èı

-0.15

emo

-0.15

posix

-0.15

raj

-0.14

adol

-0.14

owied

-0.14

stdin

-0.14

POSITIVE LOGITS

 addresses

0.29

 address

0.28

 Address

0.27

åľ°åĿĢ

0.27

 registers

0.27

 register

0.27

address

0.26

 addressing

0.26

 Addresses

0.25

 adress

0.25

Activations Density 0.063%

references to programming concepts and code-related terms

No Comments

No Known Activations