INDEX

Explanations

references to specific data packets, components, and their attributes in a structured format

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

bons

-0.14

Hao

-0.14

WithEmail

-0.14

 affair

-0.14

ubar

-0.14

uo

-0.14

affle

-0.14

ìĦ±

-0.13

OrCreate

-0.13

ivy

-0.13

POSITIVE LOGITS

 part

0.48

part

0.32

 parte

0.31

 ÑĩÐ°ÑģÑĤÑĮ

0.29

 souÄįÃ¡stÃŃ

0.28

 souÄįÃ¡st

0.27

 Ø¬Ø²Ø¡

0.27

 Part

0.26

 partie

0.26

 component

0.26

Activations Density 0.298%

references to specific data packets, components, and their attributes in a structured format

No Comments

No Known Activations