INDEX

Explanations

references to human roles and occupations, specifically in arts and media contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

-0.46

ti

-0.37

ez

-0.36

eer

-0.36

tim

-0.36

tors

-0.35

tur

-0.35

tin

-0.35

ted

-0.34

tor

-0.34

POSITIVE LOGITS

rier

0.27

rr

0.26

ship

0.24

ra

0.23

de

0.23

riers

0.23

riage

0.22

ium

0.22

iginal

0.22

red

0.21

Activations Density 0.346%

references to human roles and occupations, specifically in arts and media contexts

No Comments

No Known Activations