INDEX

Explanations

elements related to digital content formatting and access

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

-0.17

-0.16

 æīĢ

-0.16

optic

-0.15

Ø²Ø±

-0.15

æīĢ

-0.15

estic

-0.14

enk

-0.14

POSITIVE LOGITS

avra

0.15

nej

0.15

ikal

0.14

iture

0.14

į

0.14

atham

0.13

udo

0.13

ciler

0.13

 Namespace

0.13

kas

0.13

Activations Density 0.003%

elements related to digital content formatting and access

No Comments

No Known Activations