INDEX

Explanations

code structures and programming constructs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

rick

-0.19

loub

-0.15

rawer

-0.15

ebe

-0.15

Ð¶Ñĥ

-0.14

uellen

-0.14

lick

-0.14

esub

-0.14

ÎµÎ¹

-0.14

parable

-0.14

POSITIVE LOGITS

akan

0.16

aka

0.15

amac

0.14

kaÃ§

0.14

lÃ¤

0.14

ASA

0.14

ad

0.14

rust

0.13

Cha

0.13

ç³»

0.13

Activations Density 0.193%

code structures and programming constructs

No Comments

No Known Activations