INDEX

Explanations

numerical values or measurements associated with various processes or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

ãģĿ

-0.15

ë¡Ģ

-0.15

icios

-0.14

_SPI

-0.14

 capitalized

-0.13

ÎµÎº

-0.13

ebek

-0.13

ajs

-0.13

ajor

-0.13

ERV

-0.13

POSITIVE LOGITS

 fixed

0.50

 specified

0.47

 defined

0.44

fixed

0.44

 determined

0.41

specified

0.41

Fixed

0.40

 Fixed

0.40

æĮĩå®ļ

0.39

åĽºå®ļ

0.39

Activations Density 0.410%

numerical values or measurements associated with various processes or conditions

No Comments

No Known Activations