INDEX

Explanations

statistics related to player performance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

alculate

-0.15

 ì¶©

-0.15

adle

-0.15

/renderer

-0.14

adio

-0.14

 Ulus

-0.14

.dex

-0.14

 AltÄ±n

-0.14

.slim

-0.14

scenario

-0.14

POSITIVE LOGITS

ipp

0.18

bon

0.16

Lau

0.15

.handleError

0.15

 Pist

0.15

weet

0.14

 efficiency

0.14

gam

0.14

Ø±Ø§ÙĨÙĩ

0.14

 chips

0.14

Activations Density 0.105%

statistics related to player performance

No Comments

No Known Activations