INDEX

Explanations

phrases related to professional experience and positions held

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

-0.15

ilden

-0.14

 none

-0.14

adeon

-0.14

itto

-0.14

inski

-0.14

asis

-0.14

oples

-0.14

ainer

-0.14

ajes

-0.13

POSITIVE LOGITS

 prior

0.36

 Prior

0.35

Prior

0.32

prior

0.30

 previously

0.28

 previous

0.28

 Previously

0.27

Previously

0.26

 earlier

0.25

 Previous

0.24

Activations Density 0.061%

phrases related to professional experience and positions held

No Comments

No Known Activations