INDEX

Explanations

references to partnerships and collaborative efforts

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

hung

-0.18

inke

-0.16

inkle

-0.16

à¤ł

-0.16

indo

-0.15

ets

-0.14

inois

-0.14

åīĽ

-0.13

/slick

-0.13

entai

-0.13

POSITIVE LOGITS

ä¹ĭä¸Ģ

0.18

aff

0.15

 sorts

0.14

 Serge

0.14

ippet

0.14

 regards

0.14

of

0.14

HO

0.14

for

0.14

oot

0.14

Activations Density 0.212%

references to partnerships and collaborative efforts

No Comments

No Known Activations