INDEX

Explanations

statements that emphasize a basis or foundation for claims or beliefs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

åĳ³

-0.17

aspers

-0.16

REFER

-0.15

LF

-0.14

cccc

-0.14

ASTER

-0.14

ulumi

-0.14

ikel

-0.14

uer

-0.14

abay

-0.14

POSITIVE LOGITS

 principles

0.28

 principle

0.24

 premise

0.24

 premises

0.22

 experience

0.21

 experiences

0.21

 principals

0.20

 Principles

0.19

 themes

0.19

 foundation

0.19

Activations Density 0.156%

statements that emphasize a basis or foundation for claims or beliefs

No Comments

No Known Activations