INDEX

Explanations

instances of size or magnitude descriptors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

DMI

-0.16

ysi

-0.15

osit

-0.15

ohana

-0.15

icone

-0.14

vala

-0.14

OSP

-0.14

antro

-0.14

ï»¿↵↵

-0.14

 baÅŁÄ±nda

-0.14

POSITIVE LOGITS

 enough

0.82

 Enough

0.60

-en

0.54

 sufficient

0.50

Enough

0.50

EN

0.50

_en

0.48

en

0.48

.en

0.44

en

0.43

Activations Density 0.103%

instances of size or magnitude descriptors

No Comments

No Known Activations