INDEX

Explanations

mathematical symbols and notations related to equations and representations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

letes

-0.17

lsru

-0.16

reak

-0.16

lectic

-0.15

èĤĸ

-0.15

mÃ¡

-0.15

 Arch

-0.14

$MESS

-0.14

iao

-0.14

ä¸Ģåº¦

-0.14

POSITIVE LOGITS

AGR

0.17

Rnd

0.16

astro

0.16

cad

0.15

CADE

0.15

otu

0.15

 conc

0.14

webtoken

0.14

Ð¢Ðŀ

0.14

 Erica

0.14

Activations Density 0.011%

mathematical symbols and notations related to equations and representations

No Comments

No Known Activations