INDEX

Explanations

numerical information related to statistics and measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

swer

-0.16

gesi

-0.15

Ã²ng

-0.14

rez

-0.14

loff

-0.14

rof

-0.14

 Beste

-0.14

ÐºÑĤ

-0.14

-0.13

POSITIVE LOGITS

jac

0.17

 contingent

0.15

iesen

0.14

ylko

0.14

Seeder

0.14

 ÑĪÑĤ

0.13

ichten

0.13

Ã¡te

0.13

 Bear

0.13

 circular

0.13

Activations Density 0.033%

numerical information related to statistics and measurements

No Comments

No Known Activations