INDEX

Explanations

instances of legal actions and official responses to controversies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

 Hampshire

-0.27

 Bronx

-0.20

 Portsmouth

-0.20

NH

-0.19

 Staten

-0.18

NJ

-0.18

 Jersey

-0.18

 Southampton

-0.17

 Rutgers

-0.17

 Monad

-0.16

POSITIVE LOGITS

 Oklahoma

0.76

 Tulsa

0.64

OK

0.62

Ok

0.59

OK

0.53

ok

0.53

Ok

0.52

-ok

0.49

ok

0.47

_ok

0.44

Activations Density 0.026%

instances of legal actions and official responses to controversies

No Comments

No Known Activations