INDEX

Explanations

references to television networks and their programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

ully

-0.16

zcze

-0.14

éĬ

-0.14

anian

-0.14

.toObject

-0.14

Ð·Ð²

-0.13

isode

-0.13

odcast

-0.13

zione

-0.13

aurant

-0.13

POSITIVE LOGITS

 channel

0.38

 channels

0.36

channel

0.33

 Channel

0.32

 Channels

0.31

channels

0.31

-channel

0.30

 cable

0.30

 CHANNEL

0.29

.channel

0.27

Activations Density 0.176%

references to television networks and their programming

No Comments

No Known Activations