INDEX

Explanations

numerical values or references to film titles and associated content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

Kansas

-0.14

 airspace

-0.14

 newIndex

-0.14

aliyet

-0.14

Hunter

-0.14

Ymd

-0.14

Fon

-0.14

Ã©nÃ©

-0.13

.sky

-0.13

elden

-0.13

POSITIVE LOGITS

 Leon

0.34

 Persian

0.34

 Therm

0.32

 Spart

0.31

 Spartan

0.30

 Pers

0.29

 King

0.28

Pers

0.26

 Greeks

0.25

 Athens

0.25

Activations Density 0.007%

numerical values or references to film titles and associated content

No Comments

No Known Activations