INDEX

Explanations

references to the Associated Press and its reporting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

 Wich

-0.16

abouts

-0.15

ifu

-0.15

nat

-0.15

 Generation

-0.14

 spis

-0.14

icz

-0.14

ensch

-0.14

NW

-0.14

POSITIVE LOGITS

ifer

0.17

VRT

0.16

à¤¹à¤°

0.15

acula

0.15

"';

0.14

 ÙħØµ

0.14

 Powder

0.14

Å¡ov

0.14

addChild

0.14

Activations Density 0.013%

references to the Associated Press and its reporting

No Comments

No Known Activations