INDEX

Explanations

references to downloadable content and PDFs

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

lop

-0.15

alt

-0.15

 carriers

-0.14

à¤®à¤°

-0.14

lÃ¼

-0.14

RET

-0.14

Ã¡tel

-0.14

cul

-0.14

anoia

-0.14

olk

-0.13

POSITIVE LOGITS

ÅŁam

0.15

çķ

0.14

¯

0.14

alleng

0.14

inho

0.14

braco

0.14

 vÃ¡

0.14

pel

0.14

itage

0.14

 Flag

0.13

Activations Density 0.137%

references to downloadable content and PDFs

No Comments

No Known Activations