INDEX

Explanations

structured data elements, particularly in a database or technical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ors

-0.17

aine

-0.15

bourg

-0.15

 custody

-0.15

ATM

-0.14

fund

-0.14

ixo

-0.14

fruit

-0.14

 Tray

-0.14

 opport

-0.13

POSITIVE LOGITS

acket

0.15

odem

0.15

upert

0.15

PÅĻi

0.14

ØŃÙħ

0.14

KdyÅ¾

0.14

ãĢĩ

0.14

ëĮĢíĳľ

0.14

FFFF

0.14

ackets

0.14

Activations Density 0.031%

structured data elements, particularly in a database or technical context

No Comments

No Known Activations