INDEX

Explanations

elements pertaining to literary works and authorship

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

å¯¸

-0.18

Ð¾Ð³ÐµÐ½

-0.15

ML

-0.15

sx

-0.15

èĥŀ

-0.15

.codes

-0.14

LLL

-0.14

_pan

-0.14

panel

-0.14

odule

-0.14

POSITIVE LOGITS

 novel

0.21

 novels

0.21

nov

0.20

 chron

0.18

 books

0.18

DI

0.17

 Novel

0.17

 standalone

0.17

nov

0.17

 stand

0.16

Activations Density 0.068%

elements pertaining to literary works and authorship

No Comments

No Known Activations