INDEX

Explanations

references to the game "League of Legends" and related gaming terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

aggi

-0.15

uckland

-0.14

aud

-0.14

unc

-0.14

AXB

-0.14

etti

-0.14

 fond

-0.14

 CHIP

-0.13

CHIP

-0.13

UDA

-0.13

POSITIVE LOGITS

 jung

0.26

 lane

0.23

League

0.21

 League

0.20

 jungle

0.20

 kayn

0.20

LCS

0.19

ADC

0.19

ARAM

0.19

 Lane

0.18

Activations Density 0.013%

references to the game "League of Legends" and related gaming terminology

No Comments

No Known Activations