INDEX

Explanations

words associated with single individuals or single-player contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

pray

-0.16

raid

-0.16

nas

-0.16

iful

-0.15

ico

-0.15

load

-0.14

uC

-0.14

oster

-0.14

 Tale

-0.14

ibo

-0.14

POSITIVE LOGITS

tons

0.26

-handed

0.20

lette

0.18

/single

0.18

GameManager

0.15

ÐµÐ´Ð¸

0.15

GameData

0.15

éĢ¸

0.14

 giáº£n

0.14

aight

0.14

Activations Density 0.023%

words associated with single individuals or single-player contexts

No Comments

No Known Activations