INDEX

Explanations

elements related to decision-making and motivation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

unist

-0.15

ìŀĲìĿ¸

-0.15

Ìģc

-0.14

 three

-0.12

.bunifuFlatButton

-0.12

 this

-0.12

 quatre

-0.12

nop

-0.12

 every

-0.12

subclass

-0.12

POSITIVE LOGITS

 something

0.20

something

0.20

æŁĲ

0.20

Something

0.18

 either

0.17

æĪĸèĢħ

0.16

or

0.15

 maybe

0.15

 quelque

0.15

 Something

0.15

Activations Density 1.501%

elements related to decision-making and motivation

No Comments

No Known Activations