INDEX

Explanations

mentions of a specific location, place, or entity identified by the letter "P."

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

åĢī

-0.17

chter

-0.15

 tend

-0.14

ìĥĪ

-0.14

agem

-0.14

Moy

-0.14

Fon

-0.14

clid

-0.14

 tended

-0.14

URRENCY

-0.14

POSITIVE LOGITS

isa

0.28

avia

0.24

omez

0.23

orden

0.23

lov

0.22

ader

0.21

iac

0.21

.za

0.21

ecs

0.21

azard

0.21

Activations Density 0.023%

mentions of a specific location, place, or entity identified by the letter "P."

No Comments

No Known Activations