INDEX

Explanations

key details related to a title or author in a bibliographic context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

 Giul

-0.19

á»ķi

-0.15

akov

-0.15

ARRIER

-0.15

 Ð´Ð¾ÑĤ

-0.14

Persistence

-0.14

seh

-0.14

undry

-0.14

gig

-0.14

nder

-0.14

POSITIVE LOGITS

 dela

0.23

 Uygu

0.22

izon

0.20

conde

0.18

ustria

0.18

Aqu

0.18

Uy

0.17

agas

0.17

ampo

0.17

cales

0.16

Activations Density 0.029%

key details related to a title or author in a bibliographic context

No Comments

No Known Activations