INDEX

Explanations

data structures and coding elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

ree

-0.17

ings

-0.17

most

-0.17

ler

-0.16

ypad

-0.16

-0.15

↵

-0.15

ain

-0.15

POSITIVE LOGITS

Î»ÎµÎº

0.15

ehir

0.15

oret

0.14

emoc

0.14

deki

0.14

ãĥ¼ãĥĸ

0.13

 Cunning

0.13

epam

0.13

eydi

0.13

Activations Density 0.212%

data structures and coding elements

No Comments

No Known Activations