INDEX

Explanations

special characters or letters from a specific encoding or language

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

¶ģ

-0.20

-0.19

¯¼

-0.18

quia

-0.15

adays

-0.14

omm

-0.14

Ost

-0.13

¯¿

-0.13

Ð¾ÑģÑĤÐ°ÑĤ

-0.13

acco

-0.13

POSITIVE LOGITS

Į

0.16

»

0.15

 Benton

0.15

arse

0.14

ģ

0.14

legg

0.14

ļ

0.14

çµĦ

0.13

addock

0.13

Î¼Î¿Î½

0.13

Activations Density 0.007%

special characters or letters from a specific encoding or language

No Comments

No Known Activations