INDEX

Explanations

references to digital document formats and associated metadata

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

amburger

-0.15

ibName

-0.15

umer

-0.15

à¸¡à¸ķ

-0.15

orman

-0.15

astos

-0.14

 Lynch

-0.14

 Nolan

-0.14

ì²Ń

-0.14

ä»ĭ

-0.13

POSITIVE LOGITS

 propos

0.16

 compart

0.15

rium

0.14

çĬ

0.14

Î¼Î¯

0.13

pg

0.13

Ske

0.13

 Antar

0.13

empt

0.13

RG

0.13

Activations Density 0.041%

references to digital document formats and associated metadata

No Comments

No Known Activations