INDEX

Explanations

references to locations and geographic entities, particularly in Scotland

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

AMA

-0.15

uplic

-0.15

 Goodman

-0.15

 Thousand

-0.14

 Crowley

-0.14

Pom

-0.14

edef

-0.14

Ka

-0.14

kk

-0.14

ilet

-0.14

POSITIVE LOGITS

 Scottish

0.18

 Edinburgh

0.17

 Loch

0.16

Rua

0.16

ieber

0.15

abei

0.15

idak

0.15

 Angus

0.15

 Perth

0.14

ronics

0.14

Activations Density 0.185%

references to locations and geographic entities, particularly in Scotland

No Comments

No Known Activations