INDEX

Explanations

phrases conveying confusion or lack of understanding about situations or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

loat

-0.15

bas

-0.15

antz

-0.14

ÑģÑĤÐ²Ð¾ÑĢ

-0.14

 autoload

-0.14

DonaldTrump

-0.14

paginator

-0.14

.scalablytyped

-0.14

IVO

-0.13

POSITIVE LOGITS

why

0.26

 puzzle

0.22

 puzz

0.21

 puzzles

0.21

ucid

0.20

 phenomenon

0.19

 Puzzle

0.19

Why

0.19

why

0.18

 phenomena

0.18

Activations Density 0.096%

phrases conveying confusion or lack of understanding about situations or concepts

No Comments

No Known Activations