INDEX

Explanations

references to suggestions and personal opinions regarding gaming cards or decks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

tera

-0.14

 Collins

-0.14

ileo

-0.14

inke

-0.14

 Booker

-0.13

.setToolTip

-0.13

ruk

-0.13

 sale

-0.13

iros

-0.13

ysz

-0.13

POSITIVE LOGITS

 card

0.20

 cards

0.19

 Cards

0.16

çīĮ

0.16

feld

0.16

.scalablytyped

0.15

(card

0.15

agra

0.15

card

0.15

Activations Density 0.004%

references to suggestions and personal opinions regarding gaming cards or decks

No Comments

No Known Activations