INDEX

Explanations

references to shared experiences and memories

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

ila

-0.16

Interop

-0.15

itta

-0.15

bara

-0.15

iju

-0.15

lett

-0.14

iosa

-0.14

Î»Î¹ÎºÎ¬

-0.14

');?>↵

-0.14

oton

-0.14

POSITIVE LOGITS

SSI

0.23

DMI

0.20

MPI

0.20

á»Ļi

0.20

uzzi

0.20

PCI

0.19

assi

0.19

ALI

0.19

elli

0.19

MSI

0.18

Activations Density 0.036%

references to shared experiences and memories

No Comments

No Known Activations