INDEX

Explanations

numerical references or identifiers related to bills or measures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ICO

-0.15

ìĤ¬ìĹħ

-0.15

krv

-0.15

ãĤ¥

-0.14

aub

-0.14

tel

-0.14

HttpException

-0.13

agma

-0.13

ouz

-0.13

POSITIVE LOGITS

adena

0.16

abez

0.16

Bea

0.15

 penny

0.15

aden

0.15

 Penny

0.15

EA

0.14

ped

0.14

éĻĲ

0.14

ized

0.14

Activations Density 0.048%

numerical references or identifiers related to bills or measures

No Comments

No Known Activations