INDEX

Explanations

geographic locations and specific place names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

raquo

-0.18

 Peaks

-0.17

 ninh

-0.17

 peso

-0.15

uploaded

-0.15

éª

-0.14

urent

-0.14

ecko

-0.14

ÑģÐ¸Ð»ÑĮ

-0.13

NECT

-0.13

POSITIVE LOGITS

utton

0.16

 Village

0.14

 Case

0.14

imli

0.14

ificio

0.14

San

0.13

Ug

0.13

ards

0.13

Bro

0.13

Activations Density 0.144%

geographic locations and specific place names

No Comments

No Known Activations