INDEX

Explanations

references to significant architectural structures and religious buildings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

à¤¼à¥į

-0.15

enburg

-0.15

ÑģÑĤÐ¸

-0.14

ees

-0.14

_fu

-0.14

nu

-0.14

okrat

-0.13

 èĬ±

-0.13

pit

-0.13

ANEL

-0.13

POSITIVE LOGITS

ahat

0.15

åº§

0.14

wi

0.14

idth

0.14

GetCurrent

0.13

onec

0.13

 mains

0.13

 chÃ³

0.13

Zem

0.13

dic

0.13

Activations Density 0.064%

references to significant architectural structures and religious buildings

No Comments

No Known Activations