INDEX

Explanations

dialogue or quotes from individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

iesen

-0.15

odes

-0.15

thi

-0.14

Ced

-0.14

ãģ¨ãģĨ

-0.14

RECT

-0.14

á»Łi

-0.14

<+

-0.13

aktu

-0.13

oded

-0.13

POSITIVE LOGITS

ä¸Ī

0.17

ocz

0.16

.Interop

0.15

ije

0.15

.Transparent

0.15

mekte

0.14

Ã¨ne

0.14

.defer

0.14

0.13

 ÑĥÑĢÐ¾Ð¶

0.13

Activations Density 0.061%

dialogue or quotes from individuals

No Comments

No Known Activations