INDEX

Explanations

mathematical symbols and variables used in a technical document

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

ÑģÑı

-0.15

ARP

-0.15

 ÏĢÎµÏģÎ¹

-0.15

mor

-0.15

geh

-0.14

anas

-0.14

presso

-0.14

 onLoad

-0.14

ly

-0.13

aul

-0.13

POSITIVE LOGITS

âĢİ

0.18

0.15

Chi

0.15

deaux

0.14

ABCDEFGHIJKLMNOPQRSTUVWXYZ

0.14

clide

0.14

up

0.14

iny

0.13

Activations Density 0.191%

mathematical symbols and variables used in a technical document

No Comments

No Known Activations