INDEX

Explanations

mathematical expressions and variables related to statistical distributions and graph theory

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

Ð»Ð°Ð±

-0.15

razier

-0.15

weit

-0.15

)?$

-0.14

 Trojan

-0.14

 tack

-0.13

 customization

-0.13

cratch

-0.13

urd

-0.13

POSITIVE LOGITS

0.24

ï¼½

0.23

ï½Ŀ

0.20

Ãŀ

0.18

âŁ©

0.16

()\

0.15

 ...\

0.15

apid

0.15

{}\

0.15

Ú©Ø±ÛĮ

0.15

Activations Density 0.055%

mathematical expressions and variables related to statistical distributions and graph theory

No Comments

No Known Activations