INDEX

Explanations

terms and concepts related to canonical law and doctrine

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

lio

-0.15

ouch

-0.15

nika

-0.15

á»Ļ

-0.15

å·®

-0.14

endale

-0.14

orque

-0.14

rogen

-0.13

.Slf

-0.13

Stripe

-0.13

POSITIVE LOGITS

idad

0.16

cpt

0.15

lder

0.15

emoc

0.15

xygen

0.15

CPP

0.14

feit

0.14

0.13

 representations

0.13

Activations Density 0.016%

terms and concepts related to canonical law and doctrine

No Comments

No Known Activations