INDEX

Explanations

references to historical figures and events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

 ourselves

-0.15

 partager

-0.15

eldom

-0.14

_stdio

-0.14

 Foto

-0.14

ustum

-0.14

 Posting

-0.14

Ã©nom

-0.13

-www

-0.13

ìĿ´ëĿ¼

-0.13

POSITIVE LOGITS

 various

0.19

 Various

0.18

Various

0.17

unda

0.17

 progress

0.16

@mail

0.16

 Ã§eÅŁitli

0.16

urning

0.15

 inclusive

0.15

Ã£

0.14

Activations Density 0.038%

references to historical figures and events

No Comments

No Known Activations