INDEX

Explanations

references to literary works and their authors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

peare

-0.15

LLL

-0.15

 Script

-0.14

 Poetry

-0.14

Shown

-0.14

logan

-0.14

zan

-0.14

å¾¡

-0.13

 Viewer

-0.13

ua

-0.13

POSITIVE LOGITS

 novel

0.44

 Novel

0.38

 novels

0.35

nov

0.33

 novelist

0.26

nov

0.25

å°ıè¯´

0.25

Nov

0.24

ovel

0.20

 Booker

0.19

Activations Density 0.224%

references to literary works and their authors

No Comments

No Known Activations