INDEX

Explanations

references to borrowing and financial history

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

amburg

-0.15

oub

-0.14

iar

-0.14

Ø´ÙħØ§ÙĦÛĮ

-0.14

ÐµÐ½ÑĮ

-0.14

laden

-0.14

oud

-0.13

ogne

-0.13

ishop

-0.13

ottes

-0.13

POSITIVE LOGITS

 until

0.20

until

0.18

 atÃ©

0.18

Until

0.17

 Until

0.17

_now

0.16

.Now

0.16

-now

0.16

 jusqu

0.16

stad

0.16

Activations Density 0.336%

references to borrowing and financial history

No Comments

No Known Activations