INDEX

Explanations

information about organizational announcements and changes in leadership or service policies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

agg

-0.15

elu

-0.14

Stride

-0.13

Constructor

-0.13

@Before

-0.13

anon

-0.13

izar

-0.13

ame

-0.13

iap

-0.13

ames

-0.12

POSITIVE LOGITS

 effective

0.85

effective

0.76

 Effective

0.74

Effective

0.71

-effective

0.62

 beginning

0.60

 starting

0.58

 Beginning

0.51

 Starting

0.50

 EFFECT

0.49

Activations Density 0.326%

information about organizational announcements and changes in leadership or service policies

No Comments

No Known Activations