INDEX

Explanations

features and components of various products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

 Bain

-0.17

cob

-0.16

ancel

-0.15

obra

-0.15

 pall

-0.15

rias

-0.14

 trom

-0.14

rom

-0.14

ÄĽl

-0.14

POSITIVE LOGITS

.ToDouble

0.14

isu

0.14

 Logic

0.14

ÏĥÏĦÎµ

0.14

.nih

0.14

atsapp

0.14

Lint

0.13

à¤ķà¤°à¤£

0.13

ahan

0.13

/chart

0.13

Activations Density 0.496%

features and components of various products

No Comments

No Known Activations