INDEX

Explanations

discussions around democracy, governance, and political participation

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

ë¦¬ìĸ´

-0.15

 Hubbard

-0.15

/stdc

-0.15

isko

-0.15

preter

-0.14

atak

-0.14

 Ø³Ùģ

-0.13

Ä©nh

-0.13

untos

-0.13

opus

-0.12

POSITIVE LOGITS

 democracy

0.40

 representative

0.38

 democratic

0.36

 particip

0.32

 checks

0.32

-dem

0.31

 Checks

0.31

 Democracy

0.31

 democr

0.31

dem

0.30

Activations Density 0.100%

discussions around democracy, governance, and political participation

No Comments

No Known Activations