INDEX

Explanations

structured data and references to numerical or regulatory information

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

DoubleClick

-0.15

alysis

-0.15

stad

-0.14

Ã¡p

-0.14

usercontent

-0.14

jan

-0.14

utron

-0.14

unn

-0.14

.openg

-0.14

POSITIVE LOGITS

hend

0.21

ç¤

0.15

 Há»įc

0.15

à¥įà¤¤à¤ķ

0.13

Vox

0.13

æ°§

0.13

 Barth

0.13

åıĳ

0.13

imeo

0.13

Zuk

0.13

Activations Density 0.238%

structured data and references to numerical or regulatory information

No Comments

No Known Activations