INDEX

Explanations

references to the series "Game of Thrones" and its related 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

unga

-0.18

urch

-0.16

ãĤ·ãĥ¥

-0.15

acman

-0.15

urat

-0.15

 Morton

-0.15

olson

-0.14

orton

-0.14

KP

-0.14

à¸ķà¸¥

-0.14

POSITIVE LOGITS

 Thrones

0.44

 Game

0.43

HBO

0.38

GOT

0.35

Game

0.34

/Game

0.34

 GAME

0.32

Ary

0.31

 Throne

0.29

 Season

0.28

Activations Density 0.030%

references to the series "Game of Thrones" and its related content

No Comments

No Known Activations