INDEX

Explanations

various aspects of applications and functionality across different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

uen

-0.15

nore

-0.15

uentes

-0.15

aised

-0.14

uxe

-0.14

elier

-0.14

WD

-0.14

rots

-0.13

BoxLayout

-0.13

 Lith

-0.13

POSITIVE LOGITS

 uses

0.17

 purposes

0.16

ÙģØ¹

0.16

amus

0.15

 ÄĳÃŃch

0.15

åİŁæľ¬

0.15

ergus

0.14

ìļ©

0.14

 purpose

0.14

Pur

0.14

Activations Density 0.169%

various aspects of applications and functionality across different contexts

No Comments

No Known Activations