INDEX

Explanations

specific terms related to governance, planning, and policy-making

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

itzer

-0.17

çī©

-0.16

orem

-0.16

uppe

-0.15

 Moral

-0.14

bon

-0.13

czy

-0.13

nam

-0.13

ologne

-0.13

 Ð¿Ð»

-0.13

POSITIVE LOGITS

ÑģÑĤÐ¸

0.15

zyst

0.15

Ã¡lnÄĽ

0.14

Ä±rÄ±

0.14

afka

0.14

|array

0.14

 Rack

0.14

à¸¸à¸ĩ

0.14

inkel

0.14

.inst

0.13

Activations Density 0.232%

specific terms related to governance, planning, and policy-making

No Comments

No Known Activations