INDEX

Explanations

information related to leadership and professional titles

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

agos

-0.18

-0.15

CHA

-0.14

adeon

-0.14

reur

-0.14

InProgress

-0.14

atego

-0.14

Ã¡Å¾

-0.13

dma

-0.13

andas

-0.13

POSITIVE LOGITS

 prior

0.33

 Prior

0.31

Prior

0.28

prior

0.26

 Before

0.22

 before

0.20

 Previously

0.20

Before

0.20

 BEFORE

0.19

Previously

0.18

Activations Density 0.050%

information related to leadership and professional titles

No Comments

No Known Activations