INDEX

Explanations

geographic locations and 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 @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

olls

-0.15

zon

-0.15

ugin

-0.15

_Vert

-0.15

 Guild

-0.15

bris

-0.14

irts

-0.14

retty

-0.14

lands

-0.14

RT

-0.14

POSITIVE LOGITS

ãĥ³ãĥ

0.16

 Seymour

0.14

xec

0.14

mium

0.14

instein

0.14

asin

0.14

maries

0.14

Ùħ

0.14

ym

0.13

estre

0.13

Activations Density 0.143%

geographic locations and place names

No Comments

No Known Activations