INDEX

Explanations

references to companies or business entities, particularly with regards to their structure and operations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

Pon

-0.15

rep

-0.15

angan

-0.14

wald

-0.14

cratch

-0.14

bian

-0.13

Ã´m

-0.13

berman

-0.13

pace

-0.13

Convertible

-0.13

POSITIVE LOGITS

æľīéĻĲåħ¬åı¸

0.17

AAF

0.15

quire

0.14

 Belt

0.14

mbH

0.14

/Private

0.14

.createClass

0.14

uml

0.13

ASTER

0.13

esseract

0.13

Activations Density 0.039%

references to companies or business entities, particularly with regards to their structure and operations

No Comments

No Known Activations