INDEX

Explanations

examples or instances that illustrate a concept or argument

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

 plÃ¡

-0.15

tha

-0.14

cake

-0.13

éĹ

-0.13

_unref

-0.13

addock

-0.13

amoto

-0.13

 Surround

-0.13

zw

-0.13

ØªÙī

-0.13

POSITIVE LOGITS

 example

0.21

osu

0.18

 recently

0.16

ä¾ĭ

0.16

legen

0.16

yar

0.15

Ø«Ø±

0.15

 such

0.15

 Beispiel

0.15

 exemp

0.15

Activations Density 0.063%

examples or instances that illustrate a concept or argument

No Comments

No Known Activations