INDEX

Explanations

phrases indicating aspects of game performance and outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

abyrinth

-0.15

inspace

-0.14

 sounding

-0.14

Arb

-0.14

Budget

-0.14

ÑģÑıÑĤ

-0.14

budget

-0.13

 Hits

-0.13

Æ°Æ¡ng

-0.13

ÙĪÙĤ

-0.13

POSITIVE LOGITS

 figures

0.21

 Vaults

0.19

 vault

0.18

 looked

0.17

 counts

0.16

 counted

0.16

lo

0.16

 figured

0.15

ascus

0.15

Activations Density 0.089%

phrases indicating aspects of game performance and outcomes

No Comments

No Known Activations