INDEX

Explanations

specific numerical data and versioning information in documents

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

ãģ£ãģ¡

-0.16

alem

-0.15

uyo

-0.15

resolver

-0.14

prus

-0.14

ä¼ģ

-0.14

ande

-0.14

cad

-0.13

 antig

-0.13

.lu

-0.13

POSITIVE LOGITS

 Version

0.16

 indeb

0.15

thal

0.15

ipar

0.15

 getVersion

0.14

ssel

0.14

anson

0.14

Ľi

0.14

Activations Density 0.000%

specific numerical data and versioning information in documents

No Comments

No Known Activations