INDEX

Explanations

references to television networks and shows, particularly in the science fiction genre

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

unte

-0.17

-0.15

abaj

-0.15

etting

-0.14

adio

-0.14

enty

-0.14

enever

-0.14

azer

-0.14

@student

-0.13

napshot

-0.13

POSITIVE LOGITS

logo

0.15

ision

0.15

_logo

0.15

Logo

0.15

ĵn

0.14

-logo

0.14

<|

0.14

HD

0.14

 sublic

0.14

 logo

0.14

Activations Density 0.056%

references to television networks and shows, particularly in the science fiction genre

No Comments

No Known Activations