INDEX

Explanations

questions and inquiries related to evaluation and understanding processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

éĻ

-0.15

oud

-0.14

ÑģÑĤÑĭ

-0.14

.TODO

-0.14

 Ø¢ÙħØ±ÛĮÚ©

-0.13

ovit

-0.13

kop

-0.13

ari

-0.13

ario

-0.13

POSITIVE LOGITS

.TRAN

0.14

 tend

0.14

Dll

0.13

IID

0.13

emain

0.13

 Bris

0.13

BX

0.13

 Glas

0.13

weg

0.13

NES

0.13

Activations Density 0.053%

questions and inquiries related to evaluation and understanding processes

No Comments

No Known Activations