INDEX

Explanations

proper nouns related to geographical locations and possibly their characteristics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

inkel

-0.16

ideon

-0.15

gan

-0.15

 nhau

-0.15

uchs

-0.15

agar

-0.14

 notion

-0.14

idor

-0.14

 unnecessary

-0.14

icot

-0.13

POSITIVE LOGITS

ê¹

0.17

ascimento

0.14

ecessarily

0.14

emonic

0.14

emale

0.14

arios

0.14

want

0.14

Ð»Ð¾Ð¶

0.13

 Niet

0.13

areth

0.13

Activations Density 0.463%

proper nouns related to geographical locations and possibly their characteristics

No Comments

No Known Activations