INDEX

Explanations

instructions related to submission guidelines and formatting requirements

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

-0.14

ws

-0.14

igte

-0.14

Eld

-0.14

assel

-0.14

hs

-0.13

rio

-0.13

rat

-0.13

 Freedom

-0.13

 shown

-0.13

POSITIVE LOGITS

ToFit

0.16

uÃ©

0.15

named

0.15

::$_

0.15

anagan

0.15

iren

0.15

:name

0.15

Detach

0.15

ãĥ¼ãĥĩ

0.14

ABA

0.14

Activations Density 0.024%

instructions related to submission guidelines and formatting requirements

No Comments

No Known Activations