INDEX

Explanations

photo credits and attribution details related to images

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

dden

-0.17

oten

-0.16

evin

-0.15

è¼Ķ

-0.15

rrha

-0.15

iddi

-0.15

ogo

-0.15

adal

-0.14

acha

-0.14

ACH

-0.14

POSITIVE LOGITS

YRO

0.14

TPL

0.14

shots

0.13

GetInt

0.13

İ

0.13

éĥİ

0.13

swire

0.13

Yue

0.13

 Twig

0.12

ug

0.12

Activations Density 0.030%

photo credits and attribution details related to images

No Comments

No Known Activations