INDEX

Explanations

expressions of enjoyment and engagement with games

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

 stanza

-0.16

anou

-0.16

äºŃ

-0.15

 cluster

-0.15

auc

-0.15

bars

-0.15

dro

-0.14

ango

-0.14

-string

-0.14

dro

-0.14

POSITIVE LOGITS

 cards

0.23

 card

0.22

 board

0.22

 game

0.21

 gameplay

0.19

 tabletop

0.19

 Essen

0.17

Cards

0.17

 cardboard

0.17

 Cards

0.16

Activations Density 0.087%

expressions of enjoyment and engagement with games

No Comments

No Known Activations