INDEX

Explanations

references to streaming services and their features

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

ÑĭÑģ

-0.14

emony

-0.14

-REAL

-0.14

Insn

-0.13

ANTLR

-0.13

*time

-0.13

.googlecode

-0.13

Queryable

-0.13

enschaft

-0.13

-gnu

-0.13

POSITIVE LOGITS

app

0.41

App

0.33

 apps

0.29

 Apps

0.27

 Mobile

0.27

 Everywhere

0.25

 mobile

0.25

app

0.25

APP

0.25

+,

0.25

Activations Density 0.075%

references to streaming services and their features

No Comments

No Known Activations