INDEX

Explanations

negations and contexts that explore the theme of absence or non-existence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

uchar

-0.16

ddb

-0.16

ereum

-0.15

nou

-0.14

_hdl

-0.14

pcs

-0.14

ussian

-0.14

cz

-0.14

edere

-0.14

DITION

-0.14

POSITIVE LOGITS

 Canter

0.15

erties

0.15

Æ

0.15

orton

0.14

 Handy

0.14

ike

0.14

omba

0.14

amaz

0.14

 misc

0.14

ÑĢÑĥÐ´

0.14

Activations Density 0.013%

negations and contexts that explore the theme of absence or non-existence

No Comments

No Known Activations