INDEX

Explanations

documentation comments or annotations in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

aver

-0.15

ÄĲT

-0.14

eldorf

-0.14

frei

-0.14

 æ¿

-0.14

à¸°

-0.14

nt

-0.14

sou

-0.13

aines

-0.13

opoulos

-0.13

POSITIVE LOGITS

ethe

0.15

0.14

 ÑģÐµÐ±Ðµ

0.14

onec

0.14

eday

0.14

isz

0.14

mÃŃ

0.13

icina

0.13

 ourselves

0.13

Activations Density 0.005%

documentation comments or annotations in code

No Comments

No Known Activations