INDEX

Explanations

references to comic book and graphic novel collections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ÅĻÃŃ

-0.19

Daw

-0.16

hev

-0.16

Î»Î¹Îº

-0.15

 Ashe

-0.15

anik

-0.14

olumn

-0.14

annel

-0.14

icamente

-0.14

anged

-0.14

POSITIVE LOGITS

zilla

0.19

åĦ

0.15

AIT

0.15

holm

0.15

 Horton

0.14

æ¶

0.14

bard

0.13

 Politico

0.13

verage

0.13

 rele

0.13

Activations Density 0.013%

references to comic book and graphic novel collections

No Comments

No Known Activations